© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210918
    Prev
    Next
    INDEX
    Explanations

    questions, answers, numbers

    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_5_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
    ي
    2.19
    י
    1.98
    מ
    1.57
    Y
    1.55
    T
    1.36
    ק
    1.35
    ד
    1.32
    يلا
    1.29
    й
    1.27
    ה
    1.26
    POSITIVE LOGITS
    2
    1.51
    0
    1.21
    to
    1.18
    러
    1.13
    ation
    1.09
    는
    1.05
    は
    1.05
    r
    1.02
    3
    1.01
    iv
    0.98
    Activations Density 0.001%

    No Known Activations