© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79038
    Prev
    Next
    INDEX
    Explanations

    possessive '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
    。《
    0.26
    ھوں
    0.25
    லைக்
    0.24
    adă
    0.23
    \".
    0.23
    的には
    0.22
    “.
    0.22
    *,
    0.22
    ፈ
    0.22
    தாகவும்
    0.22
    POSITIVE LOGITS
    Shroud
    0.30
    瀬
    0.29
    ಣಿ
    0.27
     कामया
    0.27
     edi
    0.26
     fantasia
    0.26
    暄
    0.26
    淯
    0.26
    nde
    0.26
    mores
    0.26
    Activations Density 0.002%

    No Known Activations