© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3429
    Prev
    Next
    INDEX
    Explanations

    instances of conversational storytelling, including personal pronouns, conjunctions, and emotional words like "excited".

    oai_token-act-pair · gemini-2.0-flash

    contrast words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     >=",
    -0.57
    aronne
    -0.57
    DataBinding
    -0.56
    shots
    -0.55
    anskje
    -0.53
     Había
    -0.52
    醐
    -0.52
     HasFactory
    -0.51
     shots
    -0.51
     poffible
    -0.50
    POSITIVE LOGITS
    SerializedName
    0.59
     Erişim
    0.59
    CrossRef
    0.58
    ագրություններ
    0.56
    omyces
    0.55
     resourceCulture
    0.52
     noten
    0.52
    }{*}{
    0.51
    SourceChecksum
    0.50
    full
    0.49
    Activations Density 49.675%

    No Known Activations