© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87920
    Prev
    Next
    INDEX
    Explanations

    Currywurst, Risk, corriedale

    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_3_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
    druck
    0.67
    dj
    0.62
    dde
    0.60
    ش
    0.60
    del
    0.59
    dal
    0.58
    dg
    0.58
     at
    0.55
    شون
    0.55
    lement
    0.55
    POSITIVE LOGITS
    は
    0.90
    ի
    0.89
    י
    0.89
    ه
    0.85
    ל
    0.85
    ו
    0.84
    ي
    0.84
    מ
    0.82
    ۔
    0.82
    ی
    0.77
    Activations Density 0.001%

    No Known Activations