© 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. 7825
    Prev
    Next
    INDEX
    Explanations

    fine tuning

    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
     fine
    1.13
    fine
    1.06
    Fine
    1.04
     Fine
    0.96
     FINE
    0.89
    FINE
    0.79
    細
    0.78
     細
    0.71
    细
    0.71
     finely
    0.69
    POSITIVE LOGITS
    UPS
    0.36
    лос
    0.34
     الحمل
    0.34
    ZP
    0.34
     अश्विन
    0.33
     UPS
    0.33
     шам
    0.32
     چلا
    0.32
     kemenangan
    0.32
     encontramos
    0.32
    Activations Density 0.004%

    No Known Activations