© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25541
    Prev
    Next
    INDEX
    Explanations

    fall and autumn

    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_10_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
    t
    0.23
    end
    0.22
    6
    0.20
    ло
    0.20
    у
    0.20
    ল
    0.20
    ล
    0.19
    М
    0.19
    щите
    0.19
    В
    0.19
    POSITIVE LOGITS
     Algunos
    0.22
     Adapun
    0.22
     Από
    0.21
     Những
    0.21
     പൊ
    0.21
     tzw
    0.21
    り
    0.21
     Góc
    0.20
     Ευ
    0.20
     Đi
    0.20
    Activations Density 0.004%

    No Known Activations