© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236880
    Prev
    Next
    INDEX
    Explanations

    code identifiers

    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_46_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
     textAlign
    0.37
    Iv
    0.36
    日本
    0.36
     भ
    0.36
     alignments
    0.36
     alignment
    0.35
    หมด
    0.35
     लहरा
    0.35
    IFI
    0.35
    śred
    0.34
    POSITIVE LOGITS
     j
    0.70
     ज
    0.51
    j
    0.49
     ج
    0.48
     jau
    0.44
     ж
    0.43
     işlet
    0.42
     ప్రి
    0.41
    ｊ
    0.41
    jmath
    0.39
    Activations Density 0.001%

    No Known Activations