© 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. 12046
    Prev
    Next
    INDEX
    Explanations

    legal or customer support language, especially regarding complaints or requirements.

    oai_token-act-pair · gemini-2.0-flash

    say "action"

    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
     OFDb
    -0.58
     DbType
    -0.52
    Portale
    -0.52
    Tembelea
    -0.50
     disambiguazione
    -0.49
    Pfalz
    -0.48
    ************/
    -0.48
     pinulongan
    -0.48
    ✭✭
    -0.47
     FSB
    -0.47
    POSITIVE LOGITS
    RenderAtEndOf
    0.53
     فريبيس
    0.52
    ResumeLayout
    0.50
     noqa
    0.50
     compartir
    0.48
    netbeans
    0.48
     shared
    0.47
    exe
    0.47
     deal
    0.46
    RTEE
    0.45
    Activations Density 4.298%

    No Known Activations