© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126685
    Prev
    Next
    INDEX
    Explanations

    micros, stoic, insta, toxin, Naive

    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_37_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
    r
    0.44
    bis
    0.42
    ten
    0.41
    க்
    0.40
    gs
    0.39
    d
    0.39
    n
    0.39
    ling
    0.38
     марта
    0.38
    sh
    0.37
    POSITIVE LOGITS
    ño
    0.57
    ğ
    0.54
    će
    0.54
    şte
    0.54
    feira
    0.52
    ţa
    0.52
    ła
    0.51
    ş
    0.51
    şiv
    0.51
    ña
    0.50
    Activations Density 0.063%

    No Known Activations