© 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. 176471
    Prev
    Next
    INDEX
    Explanations

    gin

    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
     т
    0.44
     dangerously
    0.42
    (-\
    0.41
     deadline
    0.40
     कागज
    0.40
     दोहरा
    0.39
     pół
    0.39
     Aka
    0.39
     আমেরিকান
    0.39
    ക്കാര
    0.38
    POSITIVE LOGITS
    Ｂ
    0.48
    Configure
    0.47
    鵲
    0.46
    పీ
    0.45
    𝐓
    0.45
    περι
    0.44
    José
    0.43
    𝐏
    0.43
     İzmir
    0.43
    ዐይን
    0.42
    Activations Density 0.001%

    No Known Activations