© 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. 8979
    Prev
    Next
    INDEX
    Explanations

    words that are descriptive or express evaluation, likelihood, or an emotional state

    oai_token-act-pair · gemini-2.0-flash

    Names or technical jargon

    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
     drape
    -0.73
     magnificence
    -0.69
     fairness
    -0.67
     fullness
    -0.67
     uniqueness
    -0.66
     correspondence
    -0.66
     periodicity
    -0.65
     diversification
    -0.64
     barter
    -0.64
     alignment
    -0.64
    POSITIVE LOGITS
    SerializedName
    0.55
    ConstraintMaker
    0.54
     kıs
    0.53
     AssemblyProduct
    0.52
    )]=
    0.51
     kaç
    0.51
    mainAxisSize
    0.50
     regret
    0.49
     MainAxisSize
    0.49
     autorytatywna
    0.49
    Activations Density 11.248%

    No Known Activations