© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181568
    Prev
    Next
    INDEX
    Explanations

    indicator title="

    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_29_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
    SpecID
    0.41
    縄
    0.37
    önen
    0.36
    اتو
    0.35
    единенных
    0.35
    邦
    0.35
    १८
    0.34
     Ausgang
    0.34
    eyn
    0.33
    不如
    0.33
    POSITIVE LOGITS
     khoa
    0.42
     unc
    0.40
     elsewhere
    0.39
     EPA
    0.39
     multiplier
    0.38
     courtesy
    0.38
     트
    0.38
     bottle
    0.37
     amplifier
    0.37
     tâ
    0.37
    Activations Density 0.000%

    No Known Activations