© 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. 15516
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing opinions

    oai_token-act-pair · gemini-2.0-flash

    public reaction

    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
     شعب
    -0.49
     N
    -0.45
     votes
    -0.45
     box
    -0.44
     O
    -0.42
    侧
    -0.42
    quia
    -0.41
     side
    -0.41
     Main
    -0.40
     last
    -0.39
    POSITIVE LOGITS
     Roskov
    0.85
     VizieR
    0.77
     Lightboxes
    0.77
     صوتيه
    0.76
    addCriterion
    0.75
    KommentareTeilen
    0.75
     intptr
    0.73
    principalColumn
    0.73
     Audiodateien
    0.72
    TintMode
    0.72
    Activations Density 36.644%

    No Known Activations