© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125781
    Prev
    Next
    INDEX
    Explanations

    .component.ts files

    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_37_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
    ⏸
    0.38
    角度
    0.38
     zer
    0.35
     ZO
    0.35
    再
    0.35
    💾
    0.35
     stayed
    0.34
    olateral
    0.34
     لوب
    0.34
    🙆
    0.34
    POSITIVE LOGITS
    ëm
    0.41
    itele
    0.39
    emics
    0.39
    rotto
    0.38
     Felic
    0.38
     சுதந்திர
    0.38
    pá
    0.36
     മുത
    0.36
    }`,
    0.35
     मंत्रि
    0.35
    Activations Density 0.000%

    No Known Activations