© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170890
    Prev
    Next
    INDEX
    Explanations

    Alice in Wonderland

    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_20_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
    wear
    0.40
    consumption
    0.39
    olerance
    0.39
    sweet
    0.39
    ဉ
    0.38
     भावना
    0.38
    லாம்
    0.38
     ду
    0.37
    ogenous
    0.37
    marine
    0.37
    POSITIVE LOGITS
    uradaki
    0.44
     هسه
    0.43
    ólogos
    0.43
     Apo
    0.42
    BooleanField
    0.42
     chemo
    0.41
     título
    0.40
     pon
    0.40
    תוך
    0.40
    <0x07>
    0.40
    Activations Density 0.000%

    No Known Activations