© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232464
    Prev
    Next
    INDEX
    Explanations

    `Hint` followed by punctuation

    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_32_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
    CCH
    0.44
    crossentropy
    0.42
    deviceID
    0.38
    ierend
    0.36
    Supplement
    0.35
    unding
    0.35
    Series
    0.35
     يَ
    0.35
     vigorously
    0.34
    AGE
    0.34
    POSITIVE LOGITS
     hint
    0.51
     подска
    0.50
     hinted
    0.49
     hints
    0.48
     ইঙ্গিত
    0.44
     Hint
    0.43
    hint
    0.43
     संकेतों
    0.43
     desarroll
    0.41
    hints
    0.41
    Activations Density 0.000%

    No Known Activations