© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48895
    Prev
    Next
    INDEX
    Explanations

    section title or heading

    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
     Falconer
    0.43
    今後
    0.41
     গ্রাহ
    0.41
    ക്കുക
    0.38
     바람
    0.37
    今後の
    0.37
    コツ
    0.36
    柱
    0.36
     ничек
    0.35
    洸
    0.35
    POSITIVE LOGITS
    િતિ
    0.37
    ac
    0.37
     !=
    0.33
    ras
    0.33
     !==
    0.33
     deriving
    0.32
    Very
    0.32
    ContentType
    0.31
    therefore
    0.31
     compacto
    0.31
    Activations Density 0.010%

    No Known Activations