© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207690
    Prev
    Next
    INDEX
    Explanations

    co- components

    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
    -
    0.57
     arrests
    0.47
    –
    0.46
     tích
    0.45
     operates
    0.45
     arrest
    0.44
     informes
    0.42
     arrested
    0.42
     permeates
    0.42
    ־
    0.42
    POSITIVE LOGITS
    Ｍ
    0.53
    PRESENT
    0.42
    Cloth
    0.41
    Ｃ
    0.41
    dummy
    0.41
    remote
    0.40
    advanced
    0.40
    saved
    0.40
    temp
    0.40
    directions
    0.39
    Activations Density 0.000%

    No Known Activations