© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54414
    Prev
    Next
    INDEX
    Explanations

    say "punctuation"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    />
    0.44
    hati
    0.40
    Lore
    0.38
    ☐
    0.37
     People
    0.37
     />
    0.36
    ></
    0.35
     First
    0.35
     *);
    0.35
    গ্ধ
    0.35
    POSITIVE LOGITS
     "#{@
    0.45
     principalColumn
    0.43
     equipado
    0.41
    .-(
    0.40
    મ
    0.40
     गं
    0.37
     Anfang
    0.37
     इंटरनेट
    0.37
    ',{
    0.37
     zuverläss
    0.37
    Activations Density 0.003%

    No Known Activations