© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13652
    Prev
    Next
    INDEX
    Explanations

    names containing the letter sequence "raz", "ak", "ris", or "khan"

    oai_token-act-pair · gemini-2.0-flash

    names and legal/political texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ConstraintMaker
    -0.62
     unknownFields
    -0.56
    Попис
    -0.53
    AllowAnonymous
    -0.52
    IntoConstraints
    -0.51
     RemoteException
    -0.50
    كويكب
    -0.49
    SpringRunner
    -0.48
    цезда
    -0.48
    Otras
    -0.47
    POSITIVE LOGITS
    addContainerGap
    0.64
    oredCriteria
    0.59
     Transfermarkt
    0.57
     nucleation
    0.55
    abestanden
    0.54
    djangoproject
    0.53
    FileDescriptor
    0.52
    TemporalType
    0.50
    かれている
    0.50
     automatiques
    0.49
    Activations Density 0.508%

    No Known Activations