© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46042
    Prev
    Next
    INDEX
    Explanations

    reactor pattern

    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_10_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
     temperatur
    0.50
    াহরণ
    0.48
    ये
    0.47
    为了
    0.47
     hardwoods
    0.47
    у
    0.47
                
    0.46
    е
    0.46
     processors
    0.46
    *
    0.45
    POSITIVE LOGITS
    -'].
    0.58
    capac
    0.56
    XII
    0.56
    ing
    0.55
    racht
    0.53
    𝗚
    0.53
    LEMENT
    0.52
    kaart
    0.52
    functioning
    0.52
    PLICATIONS
    0.52
    Activations Density 0.000%

    No Known Activations