© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15816
    Prev
    Next
    INDEX
    Explanations

    property details

    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_34_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
     அல
    0.40
     Desire
    0.39
     movimento
    0.38
    谁
    0.38
    }|^
    0.38
    WAY
    0.37
     contag
    0.37
     recursively
    0.36
     Oasis
    0.36
     después
    0.36
    POSITIVE LOGITS
    within
    0.37
    thumbs
    0.37
    dalam
    0.36
    $-
    0.35
     blends
    0.35
    slant
    0.35
    Pend
    0.35
    Paul
    0.35
     mixtures
    0.35
    Material
    0.34
    Activations Density 0.001%

    No Known Activations