© 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. 122074
    Prev
    Next
    INDEX
    Explanations

    social housing, representation, cost

    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
    b
    0.89
    ↵↵
    0.79
    ם
    0.72
    ↵↵↵
    0.70
     Emmett
    0.62
     इंद
    0.60
    國家
    0.59
    佂
    0.58
    CC
    0.58
    える
    0.58
    POSITIVE LOGITS
    (
    0.84
     I
    0.80
    {
    0.64
    <0x88>
    0.58
    <0x8D>
    0.57
    ({\
    0.55
    و
    0.55
    t
    0.53
    )
    0.53
    kale
    0.53
    Activations Density 0.005%

    No Known Activations