© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120999
    Prev
    Next
    INDEX
    Explanations

    resource group

    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_27_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
    ']].
    0.41
    ').
    0.41
     damit
    0.39
     aumentare
    0.39
     kembali
    0.39
    ']).
    0.39
     ').
    0.38
    鿷
    0.38
    ')).
    0.38
    '));
    0.37
    POSITIVE LOGITS
     Boundaries
    0.41
    殺
    0.40
    杀
    0.37
    色
    0.37
    토
    0.37
    Rough
    0.36
     Injury
    0.36
    話
    0.36
    ト
    0.35
    Datos
    0.35
    Activations Density 0.000%

    No Known Activations