© 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. 42056
    Prev
    Next
    INDEX
    Explanations

    stopping scroll and short attention

    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
     enquête
    0.33
    чної
    0.30
    aila
    0.28
     steady
    0.28
     *}
    0.28
     graz
    0.28
     kész
    0.27
     व्हाउचर
    0.27
     personality
    0.27
    ത്ത്
    0.26
    POSITIVE LOGITS
    AppBsky
    0.28
    Roof
    0.26
     بد
    0.26
    對
    0.26
    Walls
    0.26
    Virtual
    0.26
    PILE
    0.26
    WarningLevel
    0.25
     бк
    0.25
     đối
    0.25
    Activations Density 0.079%

    No Known Activations