© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121885
    Prev
    Next
    INDEX
    Explanations

    suffixes like ia and ography

    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_3_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
    ième
    0.75
    mış
    0.73
    asını
    0.72
    ną
    0.72
    𝗻
    0.71
    developed
    0.68
    yay
    0.66
    та
    0.66
    лись
    0.66
     самых
    0.66
    POSITIVE LOGITS
    TI
    0.72
    F
    0.70
     It
    0.68
    ;
    0.66
    ل
    0.66
    ด
    0.66
    It
    0.65
    一
    0.65
    N
    0.64
    <start_of_image>
    0.63
    Activations Density 0.000%

    No Known Activations