© 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. 49402
    Prev
    Next
    INDEX
    Explanations

    Bob's name

    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
    मैंने
    0.31
     الموافق
    0.30
     объяснить
    0.29
    갭
    0.29
    暾
    0.29
    Allocator
    0.28
     ஆண்டுகளாக
    0.28
    ፩
    0.28
    ˆ
    0.28
    meyi
    0.28
    POSITIVE LOGITS
    reich
    0.31
    ita
    0.29
    needs
    0.29
     needs
    0.29
     goals
    0.28
    ile
    0.28
    iteit
    0.28
    Lat
    0.27
     biker
    0.27
     Lat
    0.27
    Activations Density 0.001%

    No Known Activations