© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6175
    Prev
    Next
    INDEX
    Explanations

    I am an AI disclaimer

    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_39_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
    \%.
    0.40
    ज़ी
    0.38
    Kisi
    0.36
    ußer
    0.35
    සා
    0.35
    ဆေး
    0.34
     hearsay
    0.34
     Dra
    0.34
    DISABLE
    0.34
    >′
    0.34
    POSITIVE LOGITS
     знаний
    0.40
     decompositions
    0.40
     знания
    0.39
     pomer
    0.37
    chore
    0.37
     conocimiento
    0.36
     jej
    0.35
     tav
    0.35
     pragmatic
    0.35
     letter
    0.34
    Activations Density 0.041%

    No Known Activations