© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36153
    Prev
    Next
    INDEX
    Explanations

    structured information

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    cumsum
    0.41
    DAAR
    0.39
     R
    0.38
     Chapman
    0.37
     Noah
    0.37
     ASA
    0.37
     Corm
    0.37
     strata
    0.36
     Birch
    0.36
    dP
    0.36
    POSITIVE LOGITS
     Alley
    0.44
    ATT
    0.40
     പര
    0.38
    att
    0.38
    omat
    0.37
    Wrapping
    0.37
    മായി
    0.36
    ằ
    0.36
    sco
    0.36
    mant
    0.36
    Activations Density 0.043%

    No Known Activations