© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134420
    Prev
    Next
    INDEX
    Explanations

    Paladin, Palantir, Palmetto, Palavas

    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_37_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
     wyją
    0.41
     inevitably
    0.41
     misuse
    0.38
    坊
    0.38
    ադ
    0.38
     tsy
    0.38
     خان
    0.37
     VO
    0.37
     Adriano
    0.37
     توضی
    0.37
    POSITIVE LOGITS
    πη
    0.39
    ᵀ
    0.38
     Palermo
    0.38
    Latch
    0.37
    ⑨
    0.37
    捉
    0.36
    Plist
    0.36
    Pal
    0.36
    Pale
    0.35
     ਵਿੱਚ
    0.35
    Activations Density 0.003%

    No Known Activations