© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1838
    Prev
    Next
    INDEX
    Explanations

    cannot and will not

    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_39_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
    Nep
    0.22
    templ
    0.20
    disamb
    0.20
    }^{-\
    0.20
     shipped
    0.20
     Bal
    0.20
    чную
    0.20
     পাঠানো
    0.20
    NBA
    0.20
    NFL
    0.19
    POSITIVE LOGITS
    UIManager
    0.24
     учре
    0.21
    ڑھ
    0.21
    itanie
    0.21
     knack
    0.21
    Titan
    0.20
     Adası
    0.20
    駈
    0.20
     kés
    0.20
    ងារ
    0.20
    Activations Density 0.200%

    No Known Activations