© 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. 8666
    Prev
    Next
    INDEX
    Explanations

    characters like backslashes, asterisks, numbers, and colons

    oai_token-act-pair · gemini-2.0-flash

    backslash

    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
     tartalomajánló
    -0.42
    Források
    -0.41
    Välislingid
    -0.41
    fromnode
    -0.40
     inder
    -0.39
     scoop
    -0.35
     SAD
    -0.33
     fou
    -0.32
     tung
    -0.32
     irr
    -0.32
    POSITIVE LOGITS
    InputBorder
    0.68
     capitolo
    0.68
     jegy
    0.68
     محفوظة
    0.67
    TagHelpers
    0.65
     stål
    0.64
    ActionCreators
    0.64
    L
    0.64
    setScene
    0.63
    clearpage
    0.63
    Activations Density 9.492%

    No Known Activations