© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 196992
    Prev
    Next
    INDEX
    Explanations

    derive, serialize, clone

    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_15_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
     ඔහුගේ
    0.53
     अग्रवाल
    0.52
     சிகிச்சை
    0.52
     Genel
    0.51
     પ્રમાણે
    0.51
     그는
    0.50
    nivel
    0.50
    氬
    0.50
     ልጅ
    0.49
    namese
    0.49
    POSITIVE LOGITS
     bitmap
    0.54
    a
    0.54
     stony
    0.48
    H
    0.48
     heli
    0.46
     granted
    0.45
     –
    0.45
     simultaneously
    0.45
     +
    0.44
     myth
    0.44
    Activations Density 0.000%

    No Known Activations