© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4230
    Prev
    Next
    INDEX
    Explanations

    French language text, especially related to technical topics like software and radio

    oai_token-act-pair · gemini-2.0-flash

    French chatting

    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
    Personendaten
    -0.66
     بيها
    -0.62
     resourceCulture
    -0.56
    oa̍t
    -0.53
    __.__
    -0.53
    kheim
    -0.52
     CallOverrides
    -0.52
    *///
    -0.50
    
    -0.49
    isNameExpr
    -0.49
    POSITIVE LOGITS
     BoxFit
    0.57
    NewUrlParser
    0.52
    runApp
    0.51
    __*/
    0.48
     financières
    0.48
     समीक्षाएं
    0.47
     Que
    0.47
    InjectAttribute
    0.47
     indisponible
    0.47
     qui
    0.46
    Activations Density 0.583%

    No Known Activations