© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13735
    Prev
    Next
    INDEX
    Explanations

    mathematical and symbolic expressions

    oai_token-act-pair · gemini-2.0-flash

    code/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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>
    -1.13
    '
    -0.53
    httphttps
    -0.51
    CppMethod
    -0.50
    /*
    -0.50
    исленность
    -0.47
    ’
    -0.47
    #
    -0.45
    arParams
    -0.44
    sizeCache
    -0.44
    POSITIVE LOGITS
    Portale
    0.60
    ByVersion
    0.59
     Púb
    0.58
     externi
    0.57
    Portail
    0.57
    ÉD
    0.53
     Havre
    0.53
    ựng
    0.52
     незавершена
    0.52
     Públicas
    0.52
    Activations Density 12.245%

    No Known Activations