© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4595
    Prev
    Next
    INDEX
    Explanations

    end of quoted text

    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
     언
    0.42
     naturaleza
    0.37
     Brat
    0.36
    ToBounds
    0.36
    蛞
    0.36
     dá
    0.35
     kobi
    0.35
     Toad
    0.35
    老大
    0.35
     Dad
    0.35
    POSITIVE LOGITS
     Cancell
    0.38
    visiae
    0.34
     androidx
    0.34
    ˜
    0.34
    넬
    0.33
    itelisted
    0.33
     Ran
    0.33
     Aren
    0.33
    忽然
    0.32
     পারেন
    0.31
    Activations Density 0.209%

    No Known Activations