© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45419
    Prev
    Next
    INDEX
    Explanations

    demand and supply diagrams

    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_3_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
     I
    0.76
     X
    0.67
     It
    0.66
    ↵
    0.66
     sx
    0.62
    </span>
    0.61
     W
    0.60
    I
    0.60
    ও
    0.60
    ian
    0.57
    POSITIVE LOGITS
    پ
    0.70
     ಮಾಡುವ
    0.68
    inosa
    0.68
    𝙨
    0.68
     доме
    0.66
    دە
    0.65
    то
    0.64
    iculaire
    0.64
     乀
    0.64
    स
    0.63
    Activations Density 0.001%

    No Known Activations