© 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. 249462
    Prev
    Next
    INDEX
    Explanations

    names

    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
     brothers
    0.74
     sisters
    0.61
     Brothers
    0.57
    brothers
    0.55
     frères
    0.52
    兄弟
    0.52
    ,%
    0.47
     Bros
    0.46
     kardeş
    0.46
    ,_
    0.46
    POSITIVE LOGITS
    ennzeichnet
    0.39
    afstand
    0.38
    лык
    0.37
    𒂠
    0.36
     ･
    0.36
    ेंटिस
    0.36
     अर्थात्
    0.35
     lengan
    0.35
     ভরা
    0.35
    vamente
    0.35
    Activations Density 0.004%

    No Known Activations