© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14733
    Prev
    Next
    INDEX
    Explanations

    partial words or characters combined with high-frequency words, suggesting a focus on textual corruption or incomplete data.

    oai_token-act-pair · gemini-2.0-flash

    suffic

    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
    føring
    -0.40
    contentPadding
    -0.39
     gjerne
    -0.35
    forhold
    -0.34
    valget
    -0.34
    sessionId
    -0.33
     følger
    -0.32
    ”،
    -0.32
    stanbul
    -0.32
    området
    -0.32
    POSITIVE LOGITS
     intptr
    0.88
    Personendaten
    0.84
    ⓧ
    0.80
    IntoConstraints
    0.79
    Hentet
    0.78
    CloseOperation
    0.76
    VIAF
    0.75
    EndContext
    0.75
     चीज़ों
    0.73
    ">—
    0.71
    Activations Density 14.875%

    No Known Activations