© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87969
    Prev
    Next
    INDEX
    Explanations

    surf and surprise

    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
    p
    0.99
    тным
    0.79
    polymer
    0.74
    padă
    0.71
     이미
    0.68
    czyny
    0.68
    mrow
    0.68
    مان
    0.68
    ковым
    0.67
    mach
    0.66
    POSITIVE LOGITS
    ES
    0.83
     l
    0.80
    AN
    0.78
    K
    0.77
     c
    0.77
     sekitar
    0.76
     b
    0.75
    AR
    0.75
     covalent
    0.75
    Q
    0.74
    Activations Density 0.002%

    No Known Activations