© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258358
    Prev
    Next
    INDEX
    Explanations

    permutation, security, square, falls, indemn

    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_22_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
    مي
    0.41
    سا
    0.40
    erequisite
    0.40
    ول
    0.40
    lr
    0.40
    ُ
    0.40
    _{
    0.40
    說
    0.39
     Say
    0.39
    লার
    0.39
    POSITIVE LOGITS
    hkse
    0.48
    useum
    0.48
     glories
    0.47
    Estamos
    0.46
     escorted
    0.45
     Estamos
    0.43
    ccnc
    0.43
     centralised
    0.43
     Executors
    0.43
    Thats
    0.43
    Activations Density 0.000%

    No Known Activations