© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242606
    Prev
    Next
    INDEX
    Explanations

    `.` `lib` `services` `decided` `greeting` `converter`

    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_40_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
     पट
    0.38
    datac
    0.37
    dat
    0.37
     testclass
    0.37
     organisme
    0.37
     Mot
    0.36
     informacion
    0.36
    슬
    0.36
    ନ
    0.36
     мо
    0.35
    POSITIVE LOGITS
     khám
    0.42
    泺
    0.42
     formatted
    0.39
     ادبی
    0.38
     Sied
    0.38
     deduced
    0.37
    formatted
    0.37
     Strick
    0.37
     ابتدائي
    0.36
     retarded
    0.36
    Activations Density 0.000%

    No Known Activations