© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175857
    Prev
    Next
    INDEX
    Explanations

    We're talking

    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_50_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
    จุบัน
    0.40
     stolet
    0.40
     cfg
    0.38
     тобой
    0.37
     मुताबिक
    0.37
     ฟ
    0.37
     মনোবল
    0.37
     तिच्या
    0.37
    или
    0.36
     rosso
    0.36
    POSITIVE LOGITS
    Ale
    0.37
    믹
    0.35
    收款
    0.35
     corred
    0.35
    լ
    0.35
    Wanted
    0.35
    lox
    0.34
     voisinage
    0.34
    Haha
    0.34
     Ale
    0.34
    Activations Density 0.008%

    No Known Activations