© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82571
    Prev
    Next
    INDEX
    Explanations

    s

    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_53_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
     BP
    0.43
     Certificate
    0.42
     Efect
    0.39
     Bache
    0.38
    Bonjour
    0.38
     Bonjour
    0.38
    డవ
    0.36
     N
    0.36
    check
    0.36
    在一起
    0.36
    POSITIVE LOGITS
    WA
    0.43
     wa
    0.41
    LC
    0.40
     XC
    0.39
     तारा
    0.38
    RC
    0.38
     стекло
    0.38
    XII
    0.38
     putra
    0.38
    dolo
    0.37
    Activations Density 0.001%

    No Known Activations