© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241778
    Prev
    Next
    INDEX
    Explanations

    goes out of scope

    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_40_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
     went
    0.69
     go
    0.64
     goes
    0.63
     gå
    0.57
    went
    0.57
     đi
    0.54
     gikk
    0.54
     갔
    0.52
     går
    0.51
     Goes
    0.51
    POSITIVE LOGITS
    सनीय
    0.43
     Bud
    0.42
     табы
    0.40
     Charming
    0.39
     LD
    0.39
    臭
    0.37
     Bu
    0.36
    WidgetItem
    0.36
     ಬು
    0.36
     Guilty
    0.36
    Activations Density 0.002%

    No Known Activations