© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50198
    Prev
    Next
    INDEX
    Explanations

    Automation

    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
     генера
    0.42
    โร
    0.40
    ീതി
    0.40
    வுகளை
    0.40
    ≿
    0.40
     listy
    0.38
    𒄿
    0.38
     പ്ര
    0.38
     사건
    0.37
    Gener
    0.37
    POSITIVE LOGITS
    同行
    0.40
    (:
    0.39
    arrage
    0.38
     prototypes
    0.36
    prot
    0.35
    Yer
    0.35
    ₫
    0.35
    goin
    0.35
    pura
    0.34
     Auditor
    0.34
    Activations Density 0.001%

    No Known Activations