© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205225
    Prev
    Next
    INDEX
    Explanations

    say "ball"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     aktiv
    0.41
     actives
    0.40
    纲
    0.40
     aktive
    0.38
     स्वि
    0.37
     actifs
    0.37
    Activ
    0.37
    ACTIV
    0.37
     هیچ
    0.36
    豁
    0.36
    POSITIVE LOGITS
     lep
    0.40
     Daw
    0.38
    MEM
    0.38
     Filip
    0.37
     आस
    0.36
    IOS
    0.36
    тила
    0.35
    correlated
    0.35
     le
    0.35
    θη
    0.35
    Activations Density 0.000%

    No Known Activations