© 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. 79484
    Prev
    Next
    INDEX
    Explanations

    code programming

    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
    ందుకు
    0.42
    up
    0.39
    anda
    0.38
     man
    0.37
    inal
    0.37
    โ
    0.37
    zit
    0.36
    ’’’’
    0.36
     EVIDENCE
    0.35
    isDisabled
    0.35
    POSITIVE LOGITS
    denom
    0.41
    Multipart
    0.39
     supervising
    0.38
     объ
    0.38
     Mulberry
    0.38
     overwhelmed
    0.37
    िरपेक्ष
    0.37
     indexBuffer
    0.36
    Marian
    0.36
    ㄇ
    0.36
    Activations Density 0.003%

    No Known Activations