© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225607
    Prev
    Next
    INDEX
    Explanations

    sequence substring

    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_10_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
    Ⲁ
    0.37
    raciones
    0.36
    σουν
    0.35
    сля
    0.34
    кати
    0.34
    Callories
    0.33
    푞
    0.33
    و
    0.32
    ﾏ
    0.31
    伥
    0.31
    POSITIVE LOGITS
    0.57
    ai
    0.40
    ip
    0.38
     be
    0.37
    il
    0.37
    ere
    0.35
    od
    0.35
    1
    0.34
    az
    0.33
    ji
    0.33
    Activations Density 0.015%

    No Known Activations