© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250715
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     stitched
    0.42
    कार्ट
    0.40
    <unused78>
    0.39
     اُ
    0.39
     proclaimed
    0.39
    damian
    0.38
     crafted
    0.38
     thok
    0.37
    ifiable
    0.37
     七
    0.36
    POSITIVE LOGITS
     minuto
    0.51
    minute
    0.50
     minute
    0.49
    Moment
    0.48
    Starts
    0.47
     Minute
    0.46
    Minute
    0.45
     στιγμή
    0.41
     минуту
    0.41
     Starts
    0.40
    Activations Density 0.000%

    No Known Activations