© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 89854
    Prev
    Next
    INDEX
    Explanations

    tags

    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_18_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
    7
    0.48
    pup
    0.44
     material
    0.43
    6
    0.43
     class
    0.42
    jp
    0.42
     wardrobe
    0.42
    土
    0.42
     konstru
    0.41
    ist
    0.41
    POSITIVE LOGITS
     danneggi
    0.50
     erzählt
    0.49
     segni
    0.47
     উপকূল
    0.47
     scrive
    0.47
    海军
    0.46
    <unused244>
    0.46
     deinem
    0.45
     verfügt
    0.45
    名为
    0.45
    Activations Density 0.003%

    No Known Activations