© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135105
    Prev
    Next
    INDEX
    Explanations

    bullet point

    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_6_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
    ו
    1.23
    ă
    1.22
    ä
    1.15
    ه
    1.00
    og
    0.98
    o
    0.93
    就
    0.93
    ü
    0.91
    و
    0.91
     fă
    0.90
    POSITIVE LOGITS
    T
    1.04
    Tone
    0.87
    TIA
    0.87
    ர்
    0.87
     SDLK
    0.84
    TT
    0.79
    %>%
    0.79
    Rigidbody
    0.79
    Tiffany
    0.78
    Bahn
    0.78
    Activations Density 0.002%

    No Known Activations