© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161880
    Prev
    Next
    INDEX
    Explanations

    per + unit

    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_2_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
     by
    1.23
     schimb
    1.23
     déc
    1.21
     في
    1.16
     سي
    1.16
     jeopardize
    1.15
     كتب
    1.14
    -
    1.13
     ສ
    1.13
    يد
    1.12
    POSITIVE LOGITS
    2
    1.47
    ہ
    1.39
    ุ
    1.26
    ون
    1.16
    ل
    1.14
    ties
    1.13
    ang
    1.13
    पुर
    1.10
    و
    1.10
    the
    1.02
    Activations Density 0.002%

    No Known Activations