© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14520
    Prev
    Next
    INDEX
    Explanations

    lily pads, *Amorphophallus titanum*, leaves, ears

    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_13_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
    il
    0.49
     denars
    0.46
    ר
    0.46
     местах
    0.46
    ка
    0.45
    ilized
    0.44
    ቁ
    0.44
    r
    0.43
    <0x0D>
    0.42
    ilo
    0.42
    POSITIVE LOGITS
    uell
    0.45
    sharing
    0.44
    ုပ်
    0.43
     政府
    0.43
     tearing
    0.43
     sharing
    0.42
     UEFI
    0.42
     blockchain
    0.42
     pourrait
    0.42
     eyelid
    0.42
    Activations Density 0.022%

    No Known Activations