© 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. 82023
    Prev
    Next
    INDEX
    Explanations

    non-English characters

    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
    忒
    0.39
    Mac
    0.38
     Burn
    0.38
     Mac
    0.37
    ệt
    0.35
     Bog
    0.34
    ᠨ
    0.34
    esus
    0.33
     telescopes
    0.33
    LEN
    0.33
    POSITIVE LOGITS
     اک
    0.42
     appro
    0.41
    㖡
    0.39
     بیس
    0.39
     constituer
    0.39
    Seamless
    0.38
    scrollHeight
    0.38
     представление
    0.38
    కర
    0.37
    லைக்
    0.37
    Activations Density 0.000%

    No Known Activations