© 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. 5933
    Prev
    Next
    INDEX
    Explanations

    equations and mathematical symbols

    oai_token-act-pair · gemini-2.0-flash

    Code/equations

    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
    </blockquote>
    -0.67
     незавершена
    -0.58
     Himo
    -0.57
    endphp
    -0.57
     gepubliceerd
    -0.54
    ležité
    -0.51
     Dernière
    -0.51
    cydow
    -0.51
    dicionado
    -0.50
    Traduction
    -0.50
    POSITIVE LOGITS
    }=[
    0.54
    }\|
    0.52
    üge
    0.51
    icin
    0.50
    elemField
    0.49
    forChild
    0.48
    cep
    0.47
    offsetof
    0.47
     أهل
    0.46
    ]^{-
    0.46
    Activations Density 2.441%

    No Known Activations