© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211206
    Prev
    Next
    INDEX
    Explanations

    crowdsourcing

    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_20_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
    HairColor
    0.48
    舗
    0.44
    푹
    0.43
     diagonalization
    0.43
     тео
    0.43
     {{-
    0.42
     idolat
    0.42
     weaving
    0.42
    裴
    0.42
    виси
    0.41
    POSITIVE LOGITS
    ีน
    0.46
    </i>
    0.45
    community
    0.44
    čiť
    0.43
    BUSINESS
    0.42
    outh
    0.41
    accia
    0.41
     καὶ
    0.41
    cann
    0.40
    attack
    0.40
    Activations Density 0.002%

    No Known Activations