© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110473
    Prev
    Next
    INDEX
    Explanations

    preliminary assessment or investigation

    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
    b
    1.73
     a
    1.33
     powied
    1.20
    c
    1.17
     be
    1.08
    bias
    1.05
    bentuk
    1.05
    av
    1.03
    ile
    1.03
    bord
    1.02
    POSITIVE LOGITS
     organizations
    1.23
    توى
    1.16
     instinct
    1.15
    тни
    1.14
     inorder
    1.13
    ల
    1.12
    тэй
    1.10
    я
    1.08
     in
    1.07
    ات
    1.07
    Activations Density 0.001%

    No Known Activations