© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14960
    Prev
    Next
    INDEX
    Explanations

    Please accept

    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_40_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
    Citizen
    0.39
     enclosed
    0.38
    God
    0.36
    Collegamenti
    0.36
     Citizen
    0.35
    Ç
    0.35
    god
    0.34
    槎
    0.34
    わかり
    0.32
    わからない
    0.32
    POSITIVE LOGITS
     treat
    0.56
     treating
    0.53
     Treat
    0.48
     Treating
    0.46
     tratar
    0.46
     ignoring
    0.45
    treating
    0.45
     treated
    0.45
     registro
    0.41
     Treats
    0.41
    Activations Density 0.003%

    No Known Activations