© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236734
    Prev
    Next
    INDEX
    Explanations

    steps, resolution, quality

    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_25_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
     worsened
    0.21
    缑
    0.21
     discernment
    0.21
     worsens
    0.21
     reinforcement
    0.20
    ܘܢ
    0.20
    퀀
    0.20
     ventral
    0.20
     beerCount
    0.20
    ީ
    0.20
    POSITIVE LOGITS
    had
    0.23
     hadde
    0.23
     avevano
    0.22
     aveva
    0.22
     again
    0.21
     Schuyler
    0.20
     avaient
    0.19
     igen
    0.19
     had
    0.19
     tinham
    0.19
    Activations Density 0.001%

    No Known Activations