© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12013
    Prev
    Next
    INDEX
    Explanations

    occurrences of present tense verbs and related words

    oai_token-act-pair · gemini-2.0-flash

    Code/foreign language errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     ModelExpression
    -0.60
    SourceChecksum
    -0.54
    Datuak
    -0.54
    redge
    -0.51
     onAnimation
    -0.50
    пин
    -0.47
    DoubleQuotes
    -0.46
    IL
    -0.46
    ansas
    -0.45
     كومونز
    -0.45
    POSITIVE LOGITS
     للاسماء
    0.57
     مشين
    0.57
    WebServlet
    0.56
    diğinde
    0.55
    Filmografie
    0.55
     auroit
    0.55
     beginnetje
    0.54
     transférez
    0.53
    ifrance
    0.53
     previa
    0.52
    Activations Density 0.140%

    No Known Activations