© 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. 202525
    Prev
    Next
    INDEX
    Explanations

    not

    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
     любить
    0.41
     unavoid
    0.41
     inescap
    0.41
    وكب
    0.40
    நோ
    0.40
     बर्फ
    0.39
    exponential
    0.39
    ぉ
    0.38
    eterminate
    0.38
    ovaní
    0.38
    POSITIVE LOGITS
     Nair
    0.44
    counts
    0.42
     zählen
    0.41
     counts
    0.41
     Leclerc
    0.39
    ινή
    0.39
     Counts
    0.38
     buena
    0.38
     хоро
    0.37
     счет
    0.37
    Activations Density 0.001%

    No Known Activations