© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2230
    Prev
    Next
    INDEX
    Explanations

    programming code snippets with keywords related to authentication, uploading, delays and time.

    oai_token-act-pair · gemini-2.0-flash

    words related to authentication mechanisms

    np_token-act-pair-logits · gpt-4o-mini

    technical/programming processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.63
     Adonis
    -0.56
     Lipschitz
    -0.54
     Inquisition
    -0.53
     Sodom
    -0.52
     Corde
    -0.51
     pulpit
    -0.50
     Samaria
    -0.50
     bilinear
    -0.50
     Phry
    -0.50
    POSITIVE LOGITS
    횟
    0.75
    WebElementEntity
    0.66
    Autoritní
    0.64
     method
    0.63
     rate
    0.61
     string
    0.60
     direction
    0.59
     bar
    0.54
     point
    0.54
     mechanism
    0.54
    Activations Density 5.397%

    No Known Activations