© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93032
    Prev
    Next
    INDEX
    Explanations

    Can

    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_60_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
    𝐖
    0.34
     цикл
    0.33
     봐
    0.32
     ڪري
    0.32
    𝒔
    0.32
    ারিং
    0.32
    핍
    0.31
    ᴡ
    0.31
    敀
    0.31
    ེ
    0.31
    POSITIVE LOGITS
     Can
    2.94
    Can
    2.73
    can
    1.59
     कैन
    1.30
    CAN
    1.30
     Kan
    1.23
     CAN
    1.16
    Kan
    1.03
     can
    1.00
     Canal
    0.89
    Activations Density 0.150%

    No Known Activations