© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 106293
    Prev
    Next
    INDEX
    Explanations

    biological entities

    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_44_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
    Ep
    0.45
    ammatory
    0.41
     எ
    0.40
    epart
    0.40
    ሣ
    0.40
     مردم
    0.39
    苇
    0.39
     ማድረግ
    0.38
    运
    0.37
    Germ
    0.36
    POSITIVE LOGITS
    eta
    0.38
     dysplasia
    0.37
     konstruk
    0.36
    geschoss
    0.36
     spool
    0.35
     ['<%=
    0.35
    toLocale
    0.35
     squint
    0.35
     borne
    0.35
     receta
    0.35
    Activations Density 0.004%

    No Known Activations