© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45363
    Prev
    Next
    INDEX
    Explanations

    between us

    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_13_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
    ت
    0.71
    Между
    0.57
    Between
    0.56
     insieme
    0.56
     together
    0.56
     tillsammans
    0.56
     tussen
    0.55
    กัน
    0.55
     BETWEEN
    0.55
     sizes
    0.54
    POSITIVE LOGITS
    rho
    0.61
    ровала
    0.60
    P
    0.60
     पुस्तिका
    0.59
     tiresome
    0.57
    ravenous
    0.57
    ровать
    0.55
    ेटर
    0.54
     bureaucratic
    0.54
     retroactive
    0.54
    Activations Density 0.026%

    No Known Activations