© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4243
    Prev
    Next
    INDEX
    Explanations

    hexadecimal code

    oai_token-act-pair · gemini-2.0-flash

    uncommon characters or symbols

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

    say "0"

    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
     
    -0.89
     F
    -0.68
     E
    -0.60
     "
    -0.57
     '
    -0.57
     T
    -0.55
     B
    -0.53
     *
    -0.51
     I
    -0.50
     $
    -0.50
    POSITIVE LOGITS
    ⓧ
    1.02
     MainAxisSize
    0.94
     itſelf
    0.89
     صوتيه
    0.88
     resourceCulture
    0.87
     Signalez
    0.87
    findpost
    0.82
     GIPHY
    0.82
    +:+
    0.81
     myſelf
    0.81
    Activations Density 3.213%

    No Known Activations