© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214960
    Prev
    Next
    INDEX
    Explanations

    Great Britain

    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_5_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
    ции
    1.19
    inie
    1.12
    kannya
    1.12
    ς
    1.12
    in
    1.10
    л
    1.09
    다면
    1.06
    ل
    1.06
    acji
    1.02
    ו
    1.02
    POSITIVE LOGITS
    that
    1.61
     that
    1.51
    th
    1.20
    on
    1.19
    for
    1.07
    of
    1.05
    tt
    1.02
    ig
    1.00
    t
    1.00
    he
    0.97
    Activations Density 0.000%

    No Known Activations