© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 422
    Prev
    Next
    INDEX
    Explanations

    code and programming related terms

    oai_token-act-pair · gemini-2.0-flash

    archaic words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     dan
    -0.58
     also
    -0.50
     sent
    -0.50
     та
    -0.49
     still
    -0.49
     EdgeInsets
    -0.48
    sent
    -0.48
     at
    -0.47
     certainly
    -0.47
    jarse
    -0.47
    POSITIVE LOGITS
     myſelf
    1.01
     Cæsar
    0.91
     Jefus
    0.89
     itſelf
    0.88
     Monfieur
    0.87
     Reſ
    0.78
     pleaſure
    0.77
     purpoſe
    0.76
    Personensuche
    0.74
     juſ
    0.74
    Activations Density 0.335%

    No Known Activations