© 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. 9043
    Prev
    Next
    INDEX
    Explanations

    references to figures, tables, and supplemental materials in scientific papers

    oai_token-act-pair · gemini-2.0-flash

    (

    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
     raiſ
    -1.02
     uſed
    -0.99
     Majefty
    -0.79
     myſelf
    -0.76
     Diſ
    -0.74
     ſta
    -0.73
     purpoſe
    -0.73
     ſhould
    -0.73
     ſte
    -0.73
     deſt
    -0.73
    POSITIVE LOGITS
    AndroidJUnit
    0.53
    Geplaatst
    0.52
    IntoConstraints
    0.49
    rungsseite
    0.47
    OGND
    0.47
    PageRoute
    0.47
     $
    0.46
     BoxDecoration
    0.45
     Wicidata
    0.45
    /'.$
    0.45
    Activations Density 12.143%

    No Known Activations