© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141400
    Prev
    Next
    INDEX
    Explanations

    to

    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
     read
    0.43
     …
    0.38
    мет
    0.37
     breit
    0.37
     practically
    0.37
    まだまだ
    0.36
    Categor
    0.36
     significantly
    0.36
    篓
    0.35
     After
    0.35
    POSITIVE LOGITS
    understand
    0.44
    ങ്കി
    0.43
    sna
    0.40
    ಊ
    0.39
     crane
    0.39
    undan
    0.39
    ngl
    0.39
     सीआर
    0.38
    zd
    0.38
     sleigh
    0.38
    Activations Density 0.000%

    No Known Activations