© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200196
    Prev
    Next
    INDEX
    Explanations

    places to visit

    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_12_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
    <0x0D>
    0.60
    ↵
    0.56
    {
    0.52
    é
    0.48
    at
    0.48
    éa
    0.48
    ore
    0.47
    in
    0.47
    ction
    0.46
    two
    0.46
    POSITIVE LOGITS
     hochwert
    0.53
     thisobject
    0.47
    劭
    0.47
    糬
    0.46
     høj
    0.45
     atthakath
    0.45
    এসসি
    0.45
     Pflicht
    0.45
     kualitas
    0.44
     visok
    0.44
    Activations Density 0.004%

    No Known Activations