© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111165
    Prev
    Next
    INDEX
    Explanations

    rhyming words like clock

    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
    ah
    1.20
    ។
    1.20
    리
    1.09
    Ｉ
    1.08
    ،
    1.01
    не
    1.00
    。
    1.00
    c
    0.99
    ၊
    0.97
    आई
    0.97
    POSITIVE LOGITS
    ر
    1.59
    u
    1.47
    лло
    1.13
    ل
    1.06
    ות
    1.05
    OS
    1.04
    ها
    1.02
    in
    1.02
    ap
    1.02
    ல்
    1.02
    Activations Density 0.000%

    No Known Activations