© 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. 6712
    Prev
    Next
    INDEX
    Explanations

    historical and political text about international disputes and war.

    oai_token-act-pair · 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
     GenerationType
    -0.60
     endwhile
    -0.56
    UnusedPrivate
    -0.54
    новниш
    -0.54
     });
    -0.53
    Datuak
    -0.52
     beginnetje
    -0.50
    Климат
    -0.50
    __':
    -0.49
     himo
    -0.48
    POSITIVE LOGITS
    priest
    0.54
    JMenu
    0.52
    ագրություններ
    0.50
    INTERRUPT
    0.50
    BeginInit
    0.50
    Packard
    0.50
    piecze
    0.49
    cognised
    0.49
     ger
    0.49
    AsUp
    0.48
    Activations Density 6.694%

    No Known Activations