© 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. 5941
    Prev
    Next
    INDEX
    Explanations

    Russian words and code snippets

    oai_token-act-pair · gemini-2.0-flash

    mixed content / code snippets

    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
     FontFamily
    -0.56
     InputDecoration
    -0.55
    calciatore
    -0.53
     hObject
    -0.50
     Sagittarius
    -0.49
     Mongol
    -0.49
     geodes
    -0.48
    batore
    -0.48
     Cardano
    -0.48
     Oppo
    -0.47
    POSITIVE LOGITS
     bezeichneter
    0.62
    дю
    0.57
    aré
    0.57
    äck
    0.56
    migrationBuilder
    0.56
    abá
    0.52
    Personensuche
    0.52
     noqa
    0.52
     piú
    0.52
    уда
    0.51
    Activations Density 4.002%

    No Known Activations