© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18006
    Prev
    Next
    INDEX
    Explanations

    you can

    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_34_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
     लाइट्स
    0.38
    }.${
    0.38
    imetre
    0.37
    prise
    0.37
    hrmacht
    0.37
     Bine
    0.36
    区的
    0.36
    alers
    0.36
    )^*
    0.36
    lights
    0.36
    POSITIVE LOGITS
     whatever
    0.66
     all
    0.59
    whatever
    0.59
     Whatever
    0.59
    Whatever
    0.59
     все
    0.53
     sebanyak
    0.53
     сколько
    0.51
     quantos
    0.51
     जितना
    0.50
    Activations Density 0.048%

    No Known Activations