© 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. 103327
    Prev
    Next
    INDEX
    Explanations

    Game, craft, or park references

    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
    om
    1.34
    ou
    1.33
    os
    1.27
    op
    1.27
    ac
    1.23
    ot
    1.22
    em
    1.16
    ه
    1.16
    ip
    1.15
    é
    1.14
    POSITIVE LOGITS
    ج
    1.25
    お客様
    1.16
    ड
    1.12
    बी
    1.05
    ସ
    1.03
    ש
    1.02
    szyst
    1.00
    大
    0.98
    ش
    0.96
    ति
    0.95
    Activations Density 0.001%

    No Known Activations