© 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. 3850
    Prev
    Next
    INDEX
    Explanations

    language used when describing political situations.

    oai_token-act-pair · gemini-2.0-flash

    negative opinions

    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
    __*/
    -0.59
    amic
    -0.56
     Roskov
    -0.49
    ima
    -0.47
    EndContext
    -0.47
    ResumeLayout
    -0.46
     EventArgs
    -0.46
    transQ
    -0.46
     erect
    -0.45
    ScopeManager
    -0.44
    POSITIVE LOGITS
    Obrázky
    0.73
    Rhestr
    0.68
    ConstraintMaker
    0.65
     '\\;'
    0.63
    @[+][
    0.59
    GIVEREF
    0.59
    ToBounds
    0.56
     оригіналу
    0.56
    談社
    0.56
    istoitu
    0.54
    Activations Density 10.563%

    No Known Activations