© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67902
    Prev
    Next
    INDEX
    Explanations

    say "h" words

    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_46_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
     interior
    0.63
     farmhouse
    0.58
     interiors
    0.57
    interior
    0.54
     intérieur
    0.51
    Interior
    0.49
     pueblos
    0.48
    宅
    0.48
     cottages
    0.46
     bungalows
    0.45
    POSITIVE LOGITS
    ズル
    0.39
     Purse
    0.38
    uffer
    0.38
    ὰ
    0.37
     पुस्तक
    0.37
    fpr
    0.37
     painstaking
    0.36
     Там
    0.36
    BtnUp
    0.36
     schme
    0.36
    Activations Density 0.004%

    No Known Activations