© 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. 6083
    Prev
    Next
    INDEX
    Explanations

    code snippets defining boolean or integer types and schema references, possibly within a JSON schema

    oai_token-act-pair · gemini-2.0-flash

    quotation mark

    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
    örté
    -0.61
     schermata
    -0.57
    hipster
    -0.57
     šķ
    -0.56
     vastaan
    -0.56
     avulla
    -0.56
     tarko
    -0.56
    walter
    -0.55
     raiſ
    -0.55
     epä
    -0.54
    POSITIVE LOGITS
     Roskov
    0.65
    oredCriteria
    0.54
    LookAnd
    0.46
     pit
    0.43
     cherchés
    0.42
     Rock
    0.42
     '{@
    0.41
    Vidite
    0.40
     Dor
    0.40
    webElementXpaths
    0.40
    Activations Density 13.794%

    No Known Activations