© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149808
    Prev
    Next
    INDEX
    Explanations

    fn

    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_59_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
     recognise
    0.44
    Run
    0.42
     झालं
    0.41
    /*'
    0.40
    See
    0.40
    getName
    0.40
    Runs
    0.40
    print
    0.40
    Be
    0.40
    Bats
    0.40
    POSITIVE LOGITS
     Integer
    0.49
     m
    0.49
     M
    0.44
    M
    0.41
    نوات
    0.40
     Mpc
    0.39
     Ils
    0.37
     INTEGER
    0.36
     Texture
    0.36
     Euh
    0.36
    Activations Density 0.002%

    No Known Activations