© 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. 17737
    Prev
    Next
    INDEX
    Explanations

    Lena followed by name

    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
    uidos
    0.36
    ConsoleText
    0.36
    MRS
    0.35
    🦯
    0.35
    Funcion
    0.34
    endedores
    0.34
     зако
    0.33
    йде
    0.33
    ന്നെ
    0.33
    Ꮞ
    0.33
    POSITIVE LOGITS
     Lag
    0.42
    蜀
    0.37
    lifecycle
    0.35
     Api
    0.35
    ራዊ
    0.34
     Brent
    0.34
    ි
    0.34
     penetrates
    0.33
     தொகை
    0.33
    템
    0.33
    Activations Density 0.011%

    No Known Activations