© 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. 155338
    Prev
    Next
    INDEX
    Explanations

    names or places

    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
     connot
    0.44
     connotations
    0.44
     봉
    0.41
     BMD
    0.40
     Boolean
    0.40
    Ｗ
    0.39
     sanitation
    0.39
     anzu
    0.37
    弯
    0.37
     harassment
    0.37
    POSITIVE LOGITS
     Obi
    0.43
    ixi
    0.41
     XIII
    0.39
    朊
    0.38
     Raton
    0.38
     Ось
    0.38
    QUADS
    0.37
     XI
    0.36
    poli
    0.35
    Alpes
    0.35
    Activations Density 0.002%

    No Known Activations