© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11301
    Prev
    Next
    INDEX
    Explanations

    comparisons

    oai_token-act-pair · gemini-2.0-flash

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -1.28
    __':
    -0.79
    __':
    -0.73
     as
    -0.65
     itſelf
    -0.62
    __":
    -0.60
    __":
    -0.52
     myſelf
    -0.51
     Vida
    -0.50
    Бахар
    -0.50
    POSITIVE LOGITS
     "..\..\..\
    0.66
    mobileqq
    0.65
     "..\..\
    0.57
    DebuggerNonUser
    0.53
    ogonal
    0.49
     елның
    0.49
    ToBounds
    0.48
    nasel
    0.48
    qrstuvwxyz
    0.48
     isNameExpr
    0.47
    Activations Density 2.382%

    No Known Activations