© 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. 75781
    Prev
    Next
    INDEX
    Explanations

    #include directives

    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
     kapsam
    0.39
     rượu
    0.37
    >−</
    0.36
     Rotation
    0.36
     Rotate
    0.36
     정확
    0.36
    PageIndex
    0.35
     umfang
    0.35
    ynge
    0.35
     Rule
    0.35
    POSITIVE LOGITS
    explored
    0.42
    нке
    0.40
    Returning
    0.39
     ಸೋ
    0.39
     постро
    0.39
    Torch
    0.37
     копи
    0.36
    汼
    0.36
    ស
    0.35
    Social
    0.35
    Activations Density 0.001%

    No Known Activations