© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54460
    Prev
    Next
    INDEX
    Explanations

    activation prompts

    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_55_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
     and
    0.50
     的
    0.49
     AND
    0.46
     occupies
    0.46
     strikingly
    0.46
     hasn
    0.45
     และ
    0.44
     hangs
    0.44
     és
    0.44
     published
    0.42
    POSITIVE LOGITS
    efined
    0.37
    LOL
    0.37
    ﹚
    0.36
    authentic
    0.35
    україн
    0.35
     통한
    0.35
    ฿
    0.35
    localization
    0.35
    teeth
    0.35
    ͡
    0.35
    Activations Density 0.063%

    No Known Activations