© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43788
    Prev
    Next
    INDEX
    Explanations

    Okay so

    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
     brooding
    0.40
     pectin
    0.40
     enmity
    0.39
    蟄
    0.38
    的历史
    0.38
    }']
    0.38
     incipient
    0.38
    ಟಕ
    0.38
     mildew
    0.37
    沉
    0.37
    POSITIVE LOGITS
    iza
    0.47
    embod
    0.44
    VE
    0.42
    我们的
    0.42
    ."),
    0.42
     কষ্ট
    0.41
     qtd
    0.41
     Cube
    0.40
    ME
    0.40
    var
    0.40
    Activations Density 0.003%

    No Known Activations