© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89224
    Prev
    Next
    INDEX
    Explanations

    critical points, maxima, minima

    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_23_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
    拒绝
    0.47
    cccn
    0.40
    ０
    0.39
    Bromo
    0.38
     अजी
    0.38
     отказа
    0.38
     याता
    0.37
    rosophila
    0.37
     Piaget
    0.37
    ?),
    0.36
    POSITIVE LOGITS
     |
    0.44
     cells
    0.43
     Responsible
    0.42
     weave
    0.42
     hairs
    0.40
     painters
    0.40
     powder
    0.39
     composers
    0.38
     peaks
    0.37
    haar
    0.37
    Activations Density 0.001%

    No Known Activations