© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193896
    Prev
    Next
    INDEX
    Explanations

    canister or NOT

    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_4_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
    us
    0.29
    ;
    0.29
     I
    0.27
    ian
    0.26
    em
    0.25
    inan
    0.24
    iving
    0.23
    ist
    0.23
    er
    0.23
    0
    0.22
    POSITIVE LOGITS
     نہيں
    0.31
    يق
    0.28
    」
    0.28
    تين
    0.28
    ：
    0.28
    ي
    0.27
    る
    0.27
    علي
    0.27
     حسين
    0.26
    一
    0.26
    Activations Density 0.002%

    No Known Activations