© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61346
    Prev
    Next
    INDEX
    Explanations

    options, options chains, option basics

    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_11_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
     titoli
    0.65
    ASX
    0.61
     caule
    0.61
    ϓ
    0.59
     मापने
    0.58
     androidx
    0.57
     بینک
    0.56
    купно
    0.55
     করিলাম
    0.55
     Moderne
    0.55
    POSITIVE LOGITS
    </h1>
    0.68
     patterns
    0.56
     patents
    0.53
    ই
    0.53
    آ
    0.50
     prototypes
    0.50
    আ
    0.49
     connections
    0.49
     hobbies
    0.49
    ヤ
    0.49
    Activations Density 0.053%

    No Known Activations