© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13120
    Prev
    Next
    INDEX
    Explanations

    hyphens used as punctuation (e.g. in number ranges or compound adjectives)

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks

    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
    w
    -1.05
    wa
    -0.82
    wed
    -0.78
    way
    -0.72
    wt
    -0.72
    wi
    -0.71
    we
    -0.70
    ws
    -0.69
    wag
    -0.69
    wd
    -0.69
    POSITIVE LOGITS
    脚注の使い方
    0.73
    bootstrapcdn
    0.60
    bkz
    0.59
    ctory
    0.57
    日閲覧
    0.56
    évaluateur
    0.52
     tartalomajánló
    0.52
    tagHelperRunner
    0.52
    BeginInit
    0.52
    bs
    0.51
    Activations Density 14.938%

    No Known Activations