© 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. 40557
    Prev
    Next
    INDEX
    Explanations

    typescript code

    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
     харак
    0.47
    Meu
    0.47
    ੀ
    0.46
     تھا۔
    0.45
    score
    0.44
     تھے
    0.44
    hean
    0.44
     nurs
    0.44
    였다
    0.42
    rice
    0.42
    POSITIVE LOGITS
    ;
    0.46
     underlies
    0.43
     abordar
    0.43
     envis
    0.43
    agog
    0.42
     manifolds
    0.42
     It
    0.41
     intelligible
    0.40
     underlining
    0.39
    entially
    0.39
    Activations Density 0.002%

    No Known Activations