© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201731
    Prev
    Next
    INDEX
    Explanations

    shows

    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_6_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
    ו
    0.96
    d
    0.87
    ୍
    0.84
     вещей
    0.79
    ल
    0.79
    ม
    0.79
     diagonals
    0.78
    я
    0.77
    ION
    0.77
    ร
    0.75
    POSITIVE LOGITS
    and
    1.45
    ari
    1.31
    é
    1.31
    as
    1.30
    is
    1.27
    id
    1.23
    un
    1.16
    ig
    1.13
    ov
    1.10
    icat
    1.09
    Activations Density 0.002%

    No Known Activations