© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177621
    Prev
    Next
    INDEX
    Explanations

    blue

    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_50_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
    দ্দা
    0.41
    SED
    0.41
    Mim
    0.40
    imab
    0.40
    輻
    0.40
    Animator
    0.39
    ActionBar
    0.38
    Clay
    0.38
    insured
    0.38
    Cork
    0.38
    POSITIVE LOGITS
     Av
    0.38
    ლო
    0.38
     vieill
    0.38
    avat
    0.37
     exter
    0.37
     Nicholson
    0.36
    ⇣
    0.36
     envej
    0.35
    ffi
    0.35
    uscany
    0.35
    Activations Density 0.000%

    No Known Activations