© 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. 4695
    Prev
    Next
    INDEX
    Explanations

    cell differentiation and proliferation

    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
     интер
    0.40
    opt
    0.39
    ینی
    0.38
     eint
    0.38
    ernum
    0.37
    斓
    0.36
     mercury
    0.36
    getPath
    0.36
     इंटर
    0.36
    ゲージ
    0.36
    POSITIVE LOGITS
    華
    0.44
    survival
    0.40
     Survival
    0.39
     unincorporated
    0.39
    GoAbroad
    0.37
    Survival
    0.37
     क्षेत्रा
    0.36
    Asia
    0.36
    🇲
    0.35
    DataFrame
    0.35
    Activations Density 0.018%

    No Known Activations