© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135097
    Prev
    Next
    INDEX
    Explanations

    linprog, info, bitbucket

    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_1_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
    -
    1.55
    4
    1.10
    ],
    1.00
     complacent
    0.94
    จะ
    0.90
     rimane
    0.90
    ,
    0.90
    ༤
    0.90
     начинается
    0.90
     pampered
    0.89
    POSITIVE LOGITS
    ru
    1.27
    se
    1.21
    re
    1.20
    sin
    1.13
    land
    1.12
    si
    1.09
    sc
    1.08
    f
    1.08
    su
    1.06
    sl
    1.05
    Activations Density 0.001%

    No Known Activations