© 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. 232460
    Prev
    Next
    INDEX
    Explanations

    clung to

    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
    電流
    0.50
     shock
    0.46
     shocks
    0.43
     chills
    0.42
     vibrations
    0.41
     veins
    0.41
     reverber
    0.41
    響
    0.41
    衝撃
    0.40
     tingling
    0.40
    POSITIVE LOGITS
     accumulate
    0.43
     attributable
    0.41
     accumulated
    0.40
     cumulative
    0.40
     achieved
    0.39
     Accumulated
    0.39
     attracted
    0.38
    fits
    0.38
    ifferential
    0.38
     aggravated
    0.38
    Activations Density 0.018%

    No Known Activations