© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 151297
    Prev
    Next
    INDEX
    Explanations

    II, a, lot, suit, Shall

    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_18_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
     GUN
    0.48
     grant
    0.44
    НІ
    0.44
     Gunners
    0.44
    ණ
    0.43
    ierge
    0.42
     uit
    0.41
     résumé
    0.41
    𝗡
    0.41
     Fast
    0.40
    POSITIVE LOGITS
    𝓬
    0.51
     lado
    0.45
    तालों
    0.44
    قامة
    0.44
    теле
    0.44
    গতকাল
    0.42
    দন
    0.42
     бота
    0.42
     cidades
    0.41
    simulator
    0.40
    Activations Density 0.000%

    No Known Activations