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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77703
    Prev
    Next
    INDEX
    Explanations

    landing page

    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_31_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
     ඉද
    0.38
     Vort
    0.38
     Commentaires
    0.36
     Mustangs
    0.35
     mounds
    0.35
     ⏮
    0.35
    )”
    0.34
    율
    0.34
    呻
    0.34
    }%
    0.34
    POSITIVE LOGITS
     bag
    0.38
    ும்பி
    0.36
    の手
    0.35
     Bag
    0.35
    chips
    0.34
     cose
    0.34
    KING
    0.33
    FUN
    0.33
     simile
    0.33
    يزات
    0.33
    Activations Density 0.006%

    No Known Activations