© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 183485
    Prev
    Next
    INDEX
    Explanations

    technical terms with definitions

    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_29_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
    +}\
    0.37
     facilitator
    0.36
     słu
    0.35
    [:-
    0.35
     обеспечивает
    0.35
     adaptar
    0.34
    食べる
    0.34
     مكون
    0.34
     prü
    0.34
    ="%
    0.33
    POSITIVE LOGITS
    znych
    0.38
    গিরই
    0.38
     Infantil
    0.37
     infantil
    0.36
     infancy
    0.36
    inson
    0.35
     cercanos
    0.34
    magic
    0.34
     của
    0.34
    질
    0.34
    Activations Density 0.015%

    No Known Activations