© 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. 42223
    Prev
    Next
    INDEX
    Explanations

    chicken thighs

    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
    的光
    0.67
    𐰣
    0.66
    ｸ
    0.65
    LD
    0.64
    एस
    0.63
    퐶
    0.61
    දු
    0.61
    ≾
    0.60
    LAN
    0.59
    CAC
    0.59
    POSITIVE LOGITS
    1
    0.88
    2
    0.79
    0.75
    "
    0.71
    at
    0.70
    0.70
    ’
    0.69
    ش
    0.69
    9
    0.67
     terceros
    0.66
    Activations Density 0.005%

    No Known Activations