© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64532
    Prev
    Next
    INDEX
    Explanations

    web links

    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_46_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
    Edward
    0.49
     Edward
    0.45
    Sal
    0.42
    ▏
    0.40
    Beta
    0.40
     Sal
    0.40
     Joaquim
    0.39
    咾
    0.38
    ␤
    0.38
    Gra
    0.38
    POSITIVE LOGITS
    በ
    0.41
    けると
    0.40
    多多
    0.39
     greens
    0.38
     eprintln
    0.38
    ್ರ
    0.37
     Aquare
    0.37
     trot
    0.37
     Cyst
    0.37
     dismantle
    0.37
    Activations Density 0.005%

    No Known Activations