© 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
    2. Gemma-3-27B-IT
    3. 39-GEMMASCOPE-2-TRANSCODER-262K
    4. 6869
    Prev
    Next
    INDEX
    Explanations

    audience

    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_39_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
    names
    0.42
    ame
    0.40
    WHO
    0.38
    Squirrel
    0.37
    urri
    0.37
    tall
    0.36
     失
    0.36
     الحق
    0.35
    iname
    0.35
    ětí
    0.35
    POSITIVE LOGITS
     favorites
    0.48
     favorite
    0.48
     favourite
    0.45
     Favorite
    0.44
     Pleasant
    0.42
     fave
    0.42
    娅
    0.40
     favourites
    0.40
     favorita
    0.40
     favoritas
    0.38
    Activations Density 0.063%

    No Known Activations