© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15812
    Prev
    Next
    INDEX
    Explanations

    a mix of negative prefixes combined with adjectives, and single-letter words

    oai_token-act-pair · gemini-2.0-flash

    negation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    __':
    -0.66
    __':
    -0.57
    tagHelperRunner
    -0.53
     biex
    -0.53
    BagConstraints
    -0.52
    execSQL
    -0.52
    TemporalType
    -0.50
    jspx
    -0.49
    ApiModelProperty
    -0.49
     priori
    -0.49
    POSITIVE LOGITS
    icose
    0.54
    sery
    0.53
    alic
    0.47
    FTFY
    0.46
    ArgsConstructor
    0.46
     الاطلاع
    0.46
    ceous
    0.45
     مرور
    0.45
    alı
    0.45
    lorette
    0.44
    Activations Density 7.339%

    No Known Activations