© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130501
    Prev
    Next
    INDEX
    Explanations

    my + noun

    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_1_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
    ק
    1.48
    ה
    1.46
    ב
    1.34
    ド
    1.20
    ли
    1.18
    ו
    1.15
     giugno
    1.12
    ే
    1.11
     marzo
    1.09
    াদ
    1.08
    POSITIVE LOGITS
    t
    1.58
    ry
    1.45
    you
    1.41
    ran
    1.32
    rl
    1.29
    ris
    1.24
    ras
    1.24
    l
    1.23
    ent
    1.23
    tive
    1.22
    Activations Density 0.000%

    No Known Activations