© 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. 30817
    Prev
    Next
    INDEX
    Explanations

    tiny bird

    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
     tlač
    0.39
    ளாக்
    0.39
    otechnical
    0.39
    verlag
    0.39
    統
    0.38
     ሌሎች
    0.38
    Redirect
    0.37
     философ
    0.36
     tong
    0.36
    㶱
    0.36
    POSITIVE LOGITS
     Hauser
    0.43
     Milwaukee
    0.40
     fate
    0.39
     syphilis
    0.37
     pleaded
    0.37
     over
    0.36
     memoir
    0.36
    tiny
    0.36
     cleaned
    0.35
     Sausage
    0.35
    Activations Density 0.039%

    No Known Activations