© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211025
    Prev
    Next
    INDEX
    Explanations

    gradual process

    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_5_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
    1
    1.98
    s
    1.84
    4
    1.80
    3
    1.65
    2
    1.63
    0
    1.51
    5
    1.43
     be
    1.26
    7
    1.25
    ่
    1.13
    POSITIVE LOGITS
    ن
    1.35
    न
    1.23
    ing
    1.17
    ă
    1.09
    ने
    1.05
    ور
    1.00
    人們
    0.99
     equilibrio
    0.96
     effectu
    0.96
     конферен
    0.95
    Activations Density 0.000%

    No Known Activations