© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258388
    Prev
    Next
    INDEX
    Explanations

    motherboards, instructions, or older

    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_22_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
    Sharing
    0.56
    Types
    0.53
     rates
    0.52
     ba
    0.51
    D
    0.51
    Gaming
    0.50
     sharing
    0.50
     Rates
    0.50
    P
    0.50
    AM
    0.49
    POSITIVE LOGITS
    قت
    0.54
    ㏄
    0.53
    aeskeygenassist
    0.52
     KJ
    0.51
    innerApiCalls
    0.50
     দ্বিত
    0.50
    nyj
    0.49
     vutta
    0.49
     natthi
    0.49
    ínt
    0.48
    Activations Density 0.000%

    No Known Activations