© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103969
    Prev
    Next
    INDEX
    Explanations

    ice cream

    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_1_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
    ب
    1.70
    م
    1.54
    מ
    1.33
     it
    1.30
     It
    1.27
    ری
    1.16
    وم
    1.16
    ە
    1.16
    ール
    1.15
     heures
    1.13
    POSITIVE LOGITS
    ↵
    1.57
    A
    1.38
    I
    1.38
    el
    1.08
    ↵↵
    0.97
    T
    0.95
    photon
    0.93
    sembles
    0.91
    retry
    0.86
     meandering
    0.86
    Activations Density 0.001%

    No Known Activations