© 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. 14303
    Prev
    Next
    INDEX
    Explanations

    HTML formatting elements

    oai_token-act-pair · gemini-2.0-flash

    data-related keywords

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

    web design code

    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
    Autoritní
    -0.88
    Personendaten
    -0.81
     мәкал
    -0.78
     propOrder
    -0.77
     Signalez
    -0.67
    exitRule
    -0.65
    chables
    -0.63
    basicConfig
    -0.63
     onPostExecute
    -0.61
     <<<<<<<<<<<<<<
    -0.60
    POSITIVE LOGITS
     ebony
    0.45
    plan
    0.42
     IDS
    0.42
     المعيارى
    0.42
    Active
    0.41
     flew
    0.41
    ps
    0.40
     morales
    0.39
     kuri
    0.39
     plan
    0.39
    Activations Density 0.509%

    No Known Activations