© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15088
    Prev
    Next
    INDEX
    Explanations

    standard practice

    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_15_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
    permanent
    0.61
    sust
    0.55
    「
    0.53
    goal
    0.52
    chairs
    0.52
    their
    0.52
    gadas
    0.52
    sup
    0.51
    shorts
    0.51
    ٦
    0.51
    POSITIVE LOGITS
     stanza
    0.59
     experi
    0.58
     >
    0.56
     ediyor
    0.55
     PLN
    0.54
     probl
    0.54
     probleml
    0.54
     reload
    0.53
     querying
    0.53
     file
    0.53
    Activations Density 0.015%

    No Known Activations