© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25165
    Prev
    Next
    INDEX
    Explanations

    crucial concepts, important considerations

    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_10_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
    স
    0.47
    ார்
    0.36
    اف
    0.36
    Т
    0.35
    म
    0.35
    多かった
    0.33
     був
    0.33
    NIA
    0.33
     கிடைத்தது
    0.33
    का
    0.33
    POSITIVE LOGITS
    性
    0.35
     confounding
    0.34
     discretion
    0.34
     monument
    0.33
     ہیں۔
    0.32
    gård
    0.32
     wrought
    0.32
     time
    0.32
    yman
    0.32
     theorem
    0.31
    Activations Density 0.014%

    No Known Activations