© 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. 78670
    Prev
    Next
    INDEX
    Explanations

    core of the model

    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
    趁
    0.35
     அதிச
    0.33
     ሴ
    0.33
    匤
    0.32
     premieres
    0.32
    includes
    0.32
    represents
    0.30
    incredible
    0.30
    ग्राउंड
    0.30
     বুঝি
    0.30
    POSITIVE LOGITS
     +'
    0.37
    ામ
    0.34
     modus
    0.33
     ('
    0.33
    ,'
    0.33
     flue
    0.31
     monument
    0.30
     temperature
    0.30
     act
    0.29
     elektronic
    0.29
    Activations Density 0.014%

    No Known Activations