© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 4372
    Prev
    Next
    INDEX
    Explanations

    icon fill states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_38_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
    嵯
    0.44
    zky
    0.42
    ิตร
    0.42
    伸び
    0.40
    وڑ
    0.40
    perg
    0.39
    achu
    0.38
     განს
    0.38
     الصف
    0.37
    孢
    0.37
    POSITIVE LOGITS
     fill
    0.61
     filled
    0.56
    Filled
    0.55
     Filled
    0.52
     filling
    0.52
    Fill
    0.52
     outline
    0.51
     Fill
    0.49
    fill
    0.49
    filled
    0.49
    Activations Density 0.005%

    No Known Activations