© 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. 126215
    Prev
    Next
    INDEX
    Explanations

    founded

    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
     Vorsitz
    0.57
    t
    0.53
    ties
    0.52
     PET
    0.52
     natürliche
    0.52
    বিদ
    0.52
    型的
    0.52
     vanligt
    0.52
    는
    0.52
     Secondo
    0.51
    POSITIVE LOGITS
    o
    0.83
    ၁
    0.75
    ır
    0.67
    к
    0.66
    あら
    0.65
    RIST
    0.64
    et
    0.63
    a
    0.63
    н
    0.63
    allocation
    0.61
    Activations Density 0.000%

    No Known Activations