© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81545
    Prev
    Next
    INDEX
    Explanations

    languages, Arabic, English

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     الض
    0.44
    Hons
    0.43
     هد
    0.40
     ض
    0.40
     ्
    0.40
     اض
    0.40
    लान
    0.39
    智能化
    0.39
    هد
    0.38
    Systems
    0.38
    POSITIVE LOGITS
    fo
    0.41
    ossal
    0.40
     ту
    0.39
     fo
    0.39
    ㎜
    0.38
    Dto
    0.38
    foe
    0.38
     fxg
    0.38
    Line
    0.37
     Tu
    0.37
    Activations Density 0.003%

    No Known Activations