© 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. 7527
    Prev
    Next
    INDEX
    Explanations

    words or characters from a mix of Bahasa, slang and English used in internet forum posts

    oai_token-act-pair · gemini-2.0-flash

    Foreign Language/Code

    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
    Personensuche
    -0.71
    ンダント
    -0.66
    GraphicsUnit
    -0.63
    rrggbb
    -0.63
     BoxFit
    -0.61
    istice
    -0.59
     تضيفلها
    -0.56
     TextInputType
    -0.56
    InputBorder
    -0.54
    帖最后由
    -0.54
    POSITIVE LOGITS
    UnsafeEnabled
    0.52
    Linha
    0.46
    InitVars
    0.45
     iyong
    0.45
    ésultat
    0.45
    StoreMessageInfo
    0.44
    ENDIF
    0.44
     jdbcTemplate
    0.43
    belli
    0.43
    xpress
    0.42
    Activations Density 0.328%

    No Known Activations