© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21362
    Prev
    Next
    INDEX
    Explanations

    AB

    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_56_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
    uell
    0.44
    ually
    0.41
    足
    0.39
    गे
    0.37
    ges
    0.37
     abl
    0.37
    족
    0.36
    schr
    0.35
    эф
    0.35
    pey
    0.34
    POSITIVE LOGITS
    pośred
    0.44
    蜞
    0.41
    ILI
    0.39
    リューム
    0.38
     Alexa
    0.38
    储备
    0.37
    ड्डी
    0.36
    リュ
    0.36
    Assist
    0.36
    Alexandra
    0.36
    Activations Density 0.002%

    No Known Activations