© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9399
    Prev
    Next
    INDEX
    Explanations

    .compile, malloc, linspace, low

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FFEE
    0.37
    BUF
    0.37
    akor
    0.37
    виси
    0.36
    ylob
    0.36
    బు
    0.35
    인이
    0.35
     調
    0.35
     حف
    0.35
    ToExp
    0.34
    POSITIVE LOGITS
    Alt
    0.38
     Mata
    0.38
    消毒
    0.37
     separable
    0.37
     assault
    0.36
     Divider
    0.36
    DAMAGE
    0.36
     Md
    0.35
     pleading
    0.35
    Md
    0.35
    Activations Density 0.027%

    No Known Activations