© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3494
    Prev
    Next
    INDEX
    Explanations

    exploring challenges and promising directions

    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_39_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
    bewegung
    0.29
    过程中
    0.28
    過程中
    0.27
    的过程中
    0.25
     जबाब
    0.25
    Emotional
    0.25
    Fantastic
    0.24
    뒹
    0.24
    fantastic
    0.24
    strange
    0.23
    POSITIVE LOGITS
    㓈
    0.26
     Investig
    0.26
     Explor
    0.26
    㑬
    0.25
     inherit
    0.25
     trackers
    0.25
    ᑭ
    0.24
     explot
    0.24
     Info
    0.24
     kajian
    0.24
    Activations Density 0.125%

    No Known Activations