© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 87260
    Prev
    Next
    INDEX
    Explanations

    CI/CD pipeline configuration: agent, environment, image

    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_18_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
     bisog
    0.47
    ujjati
    0.47
     stesse
    0.46
    Sebagai
    0.46
     डाइजेस्टिव
    0.45
     Otago
    0.44
    结尾
    0.44
    玴
    0.44
    顗
    0.44
    veyard
    0.44
    POSITIVE LOGITS
    get
    0.50
    オフィス
    0.49
    エアコン
    0.49
    程
    0.48
    not
    0.47
    co
    0.47
     pollin
    0.47
    #
    0.47
     maximize
    0.46
    arrange
    0.46
    Activations Density 0.000%

    No Known Activations