© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10267
    Prev
    Next
    INDEX
    Explanations

    code syntax related to types, returns, and values

    oai_token-act-pair · gemini-2.0-flash

    code and file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ⓧ
    -0.90
    PerformLayout
    -0.87
     Réponses
    -0.78
    GEBURTSDATUM
    -0.67
    SharedDtor
    -0.66
    Permalink
    -0.66
     iprot
    -0.66
    StructEnd
    -0.65
    Rhestr
    -0.63
     विश्वसनीयता
    -0.63
    POSITIVE LOGITS
     také
    0.56
     nej
    0.49
    Gambas
    0.45
     sa
    0.41
     виправивши
    0.39
    })(\
    0.38
    Будь
    0.38
     ganzen
    0.38
    .
    0.37
     poh
    0.36
    Activations Density 0.976%

    No Known Activations