© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10293
    Prev
    Next
    INDEX
    Explanations

    DNA sequences composed of the bases A, T, G, and C

    oai_token-act-pair · gemini-2.0-flash

    genetic sequences

    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
    SPS
    -0.41
    7
    -0.40
    SCP
    -0.40
     tamu
    -0.39
    ند
    -0.39
    SF
    -0.36
    SGS
    -0.35
     Sentinel
    -0.35
     desigual
    -0.35
    VSS
    -0.35
    POSITIVE LOGITS
     Efq
    0.98
     myſelf
    0.94
    featureID
    0.92
     ModelExpression
    0.90
    tagHelperRunner
    0.89
     Beecher
    0.88
     <<<<<<<<<<<<<<
    0.88
    IntoConstraints
    0.86
     raiſ
    0.86
     ſeveral
    0.86
    Activations Density 15.711%

    No Known Activations