© 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. 205399
    Prev
    Next
    INDEX
    Explanations

    foreign scripts

    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
     waxay
    0.40
    ܨ
    0.39
     р
    0.38
     avoided
    0.38
     chronograph
    0.37
     ENS
    0.37
     Sidd
    0.36
    љ
    0.36
    وی
    0.35
     Hodges
    0.35
    POSITIVE LOGITS
     sefer
    0.41
     thưởng
    0.40
    Gone
    0.40
    سه
    0.38
     Render
    0.38
     पसर
    0.38
    rendered
    0.37
    Raise
    0.37
     Dull
    0.37
     फैलता
    0.36
    Activations Density 0.003%

    No Known Activations