© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175542
    Prev
    Next
    INDEX
    Explanations

    package manager install commands

    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_24_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
     dakkh
    0.44
    gcash
    0.42
    uld
    0.42
     berikutnya
    0.41
    桉
    0.41
    шчы
    0.39
     puriso
    0.39
     dab
    0.38
     অবলম্বন
    0.38
    拣
    0.38
    POSITIVE LOGITS
     бед
    0.42
    rédients
    0.41
     resentment
    0.41
     protéger
    0.41
    Puedes
    0.40
    ngày
    0.38
    áj
    0.37
     phrase
    0.37
    isterschaften
    0.37
    Г
    0.37
    Activations Density 0.003%

    No Known Activations