© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150529
    Prev
    Next
    INDEX
    Explanations

    and much more

    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_23_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
    eningrad
    0.31
    賓
    0.30
    nutí
    0.30
    लक
    0.29
    od
    0.28
    hutang
    0.27
     ず
    0.27
     집
    0.26
    mba
    0.26
     മാത്രമേ
    0.26
    POSITIVE LOGITS
     digitalisation
    0.34
     vode
    0.34
     digitalization
    0.33
     voda
    0.32
    рыва
    0.32
     corticosteroids
    0.31
     voicemail
    0.30
     piel
    0.30
     enfin
    0.30
     calles
    0.30
    Activations Density 0.005%

    No Known Activations