© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34513
    Prev
    Next
    INDEX
    Explanations

    VPN plugins

    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_7_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
    :
    0.30
    F
    0.27
    会
    0.27
    %
    0.26
    >
    0.26
    ;
    0.26
     大
    0.25
    B
    0.25
    （
    0.25
    都
    0.25
    POSITIVE LOGITS
    ey
    0.32
    ed
    0.27
    ação
    0.26
    så
    0.26
    ியாக
    0.24
    ie
    0.23
    en
    0.23
    ani
    0.23
    lø
    0.23
    aal
    0.23
    Activations Density 0.002%

    No Known Activations