© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4750
    Prev
    Next
    INDEX
    Explanations

    a mixture of seemingly random characters and abbreviations, possibly related to encoding errors and Hebrew characters

    oai_token-act-pair · gemini-2.0-flash

    code snippets and languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    、
    -0.60
     and
    -0.56
    和
    -0.53
    出
    -0.48
    バ
    -0.48
    在
    -0.46
    中
    -0.45
    相
    -0.45
     or
    -0.43
    と
    -0.43
    POSITIVE LOGITS
     resourceCulture
    0.98
    ########.
    0.94
    WriteBarrier
    0.92
    ंदीखरीदारी
    0.91
    +#+#
    0.90
     ModelExpression
    0.90
    Personensuche
    0.90
    LookAnd
    0.90
     <>",
    0.87
     Roskov
    0.86
    Activations Density 0.496%

    No Known Activations