© 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. 6068
    Prev
    Next
    INDEX
    Explanations

    music and video titles

    oai_token-act-pair · gemini-2.0-flash

    technical specifications/code

    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
    UserScript
    -0.65
    省市镇
    -0.62
    XmlAccessType
    -0.62
     ujednoznacz
    -0.60
    Попис
    -0.59
    MLLoader
    -0.57
    principalTable
    -0.57
    Initializable
    -0.57
    waitKey
    -0.57
     iprot
    -0.57
    POSITIVE LOGITS
     sympathies
    0.48
     superficial
    0.47
    uver
    0.47
     supposing
    0.47
     synchronize
    0.47
     symbo
    0.46
     Hypothe
    0.44
     Syn
    0.44
     sync
    0.43
     laude
    0.43
    Activations Density 2.508%

    No Known Activations