© 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. 8837
    Prev
    Next
    INDEX
    Explanations

    loading torch models

    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
    娼
    0.35
    acane
    0.35
     तम्
    0.32
    ニコ
    0.32
    cemment
    0.31
    omes
    0.30
    unde
    0.30
    ológicos
    0.30
    lycerin
    0.30
     compet
    0.30
    POSITIVE LOGITS
    gus
    0.39
    पुर
    0.38
     क्ल
    0.36
     இடை
    0.36
    呔
    0.36
    செல்
    0.35
    インタビュー
    0.35
    hai
    0.35
    SwapChain
    0.35
     Toss
    0.34
    Activations Density 0.004%

    No Known Activations