© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257787
    Prev
    Next
    INDEX
    Explanations

    form data uploads

    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_22_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
     اړ
    0.39
    Slots
    0.38
    瘦
    0.38
    碐
    0.38
     seseorang
    0.37
    轻易
    0.37
    痩
    0.37
    :**
    0.36
     someone
    0.36
    asketball
    0.36
    POSITIVE LOGITS
    Logo
    0.40
     EAC
    0.39
    лу
    0.39
    ocal
    0.38
    WEB
    0.38
     objeto
    0.38
    faz
    0.38
    CheckingType
    0.38
    ្វី
    0.37
    宥
    0.37
    Activations Density 0.001%

    No Known Activations