© 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. 82709
    Prev
    Next
    INDEX
    Explanations

    data structure diagrams

    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
    culpa
    0.39
    㽚
    0.37
    Ĉ
    0.37
    cev
    0.36
    jal
    0.36
    jut
    0.35
    を満
    0.35
    
    0.35
     ड
    0.35
     pension
    0.35
    POSITIVE LOGITS
    рите
    0.41
    GISLATIVE
    0.40
    ቢያ
    0.38
    嗬
    0.37
     ide
    0.37
     Slade
    0.36
     पाली
    0.36
     зак
    0.36
     unrivalled
    0.35
     내용은
    0.35
    Activations Density 0.001%

    No Known Activations