© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 65490
    Prev
    Next
    INDEX
    Explanations

    hoc hic

    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_51_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
     abr
    0.42
     ئەم
    0.38
     Sham
    0.38
     лі
    0.37
     Neil
    0.37
     Evers
    0.36
    strs
    0.36
     t
    0.36
     substr
    0.35
    δη
    0.35
    POSITIVE LOGITS
     H
    0.52
    hoc
    0.51
     ہ
    0.50
     hoc
    0.50
     Hic
    0.49
     Hoc
    0.48
     Async
    0.48
     hote
    0.48
     h
    0.47
    HCl
    0.43
    Activations Density 0.015%

    No Known Activations