© 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. 262046
    Prev
    Next
    INDEX
    Explanations

    working with

    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
    ci
    0.46
    Israel
    0.41
    蜇
    0.41
    isActive
    0.40
    noc
    0.40
    acariy
    0.39
    aghi
    0.39
    确保
    0.39
    Germany
    0.39
    during
    0.39
    POSITIVE LOGITS
     wykorzyst
    0.45
    នៃ
    0.45
     활용
    0.44
    لک
    0.44
     lovely
    0.42
     powerfully
    0.42
     vertebrae
    0.42
    ־
    0.42
     inaug
    0.41
     utilización
    0.41
    Activations Density 0.010%

    No Known Activations