© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150183
    Prev
    Next
    INDEX
    Explanations

    holding

    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_23_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
     громадян
    0.35
    Citizens
    0.34
    警
    0.33
    ヴェル
    0.33
     샤
    0.32
     Renew
    0.32
    žen
    0.32
    没人
    0.32
     граждан
    0.31
     trà
    0.31
    POSITIVE LOGITS
     timeCounter
    0.42
    ktir
    0.40
    棰
    0.39
     terminator
    0.39
     metaf
    0.38
    iritual
    0.38
     attaching
    0.38
    㓞
    0.37
    struktur
    0.37
     inhaling
    0.37
    Activations Density 0.006%

    No Known Activations