© 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. 8961
    Prev
    Next
    INDEX
    Explanations

    numerical quantities or mathematical operators

    oai_token-act-pair · gemini-2.0-flash

    IDs and codes

    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
    bug
    -0.49
    kel
    -0.47
    duck
    -0.46
    UCK
    -0.45
    buff
    -0.45
    oporosis
    -0.45
    phy
    -0.44
    bry
    -0.44
    got
    -0.44
    cou
    -0.44
    POSITIVE LOGITS
    expandindo
    0.68
     AspNetCore
    0.63
     XNUMX
    0.61
    ".
    0.60
    NUMX
    0.60
     Majefty
    0.56
    .",
    0.55
     :—
    0.54
     Diſ
    0.53
    .";
    0.52
    Activations Density 22.613%

    No Known Activations