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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12388
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are politically charged or provocative, sometimes related to racial issues or stereotypes.

    oai_token-act-pair · gemini-2.0-flash

    internet content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    migrationBuilder
    -0.73
     jajaja
    -0.63
    principalColumn
    -0.60
    tagHelperRunner
    -0.60
     فريبيس
    -0.60
    ConstraintMaker
    -0.59
     مرئيه
    -0.59
     romantique
    -0.58
    WithMany
    -0.56
    ?!!
    -0.56
    POSITIVE LOGITS
     Мексичка
    0.54
     cal
    0.54
    cessite
    0.50
    UTRAL
    0.50
    eeper
    0.48
    Personensuche
    0.46
     Ar
    0.46
    getWriter
    0.46
     ar
    0.45
     pure
    0.45
    Activations Density 2.524%

    No Known Activations