© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51364
    Prev
    Next
    INDEX
    Explanations

    sliver

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     следующих
    0.38
     rom
    0.37
     Avant
    0.37
    ]-\
    0.37
     ingat
    0.37
     مساعد
    0.37
     folgenden
    0.37
     avocado
    0.36
     latest
    0.36
    应用的
    0.36
    POSITIVE LOGITS
    ond
    0.43
    often
    0.42
    atar
    0.41
     Tuti
    0.41
    োড
    0.40
    广
    0.40
    UG
    0.40
    プリング
    0.39
    omenclature
    0.38
    ัก
    0.38
    Activations Density 0.014%

    No Known Activations