© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45863
    Prev
    Next
    INDEX
    Explanations

    only if you

    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_22_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
    ကို
    0.41
    ni
    0.39
     auquel
    0.38
    問題を
    0.38
    ci
    0.38
    cm
    0.37
    éf
    0.37
    ⁹
    0.36
    jas
    0.36
    Ex
    0.36
    POSITIVE LOGITS
    跏
    0.46
    Ⲕ
    0.45
    ണ്യ
    0.45
    檄
    0.44
    ابق
    0.42
    蜞
    0.42
    пени
    0.41
    امی
    0.41
    OLDER
    0.41
    онер
    0.40
    Activations Density 0.002%

    No Known Activations