© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38102
    Prev
    Next
    INDEX
    Explanations

    ground truth

    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_3_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
    u
    0.80
    в
    0.75
     persoane
    0.72
    т
    0.71
    id
    0.69
    સ
    0.69
     qualquer
    0.68
     receb
    0.67
    ق
    0.66
    ব
    0.64
    POSITIVE LOGITS
    7
    0.76
    istä
    0.59
    AA
    0.59
    gning
    0.59
    ke
    0.58
    NE
    0.57
    8
    0.56
    äns
    0.55
    не
    0.55
    gn
    0.55
    Activations Density 0.007%

    No Known Activations