© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107847
    Prev
    Next
    INDEX
    Explanations

    Petersburg, underspending, underlying principle

    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_2_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
    ك
    1.98
    ش
    1.70
    ta
    1.61
    ng
    1.54
    مر
    1.49
    tt
    1.48
    the
    1.48
    و
    1.45
    ח
    1.44
    ุ
    1.43
    POSITIVE LOGITS
     for
    1.68
    -
    1.38
    '
    1.34
     was
    1.33
    ០
    1.20
    ேன்
    1.18
    ↵
    1.12
    elten
    1.11
    ação
    1.10
    uje
    1.10
    Activations Density 0.001%

    No Known Activations