© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216831
    Prev
    Next
    INDEX
    Explanations

    subsequent parts

    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_50_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
    Ⲑ
    0.35
     হয়তো
    0.35
     كنت
    0.35
     ይችላል
    0.34
     લઈ
    0.34
     ಅದರ
    0.34
    okok
    0.34
    akov
    0.34
    ustellen
    0.33
    <0x18>
    0.33
    POSITIVE LOGITS
    therly
    0.40
    ounding
    0.39
    ller
    0.38
    ceeded
    0.37
    oretical
    0.36
    anganese
    0.35
    ilted
    0.35
    ⁰
    0.34
    Il
    0.34
    fclose
    0.33
    Activations Density 0.007%

    No Known Activations