© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2382
    Prev
    Next
    INDEX
    Explanations

    sub graph

    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_40_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
    じゃない
    0.35
    Modification
    0.34
    发展
    0.33
     घरेलू
    0.32
     przyczyn
    0.32
    襲
    0.32
     اعزائي
    0.32
    뱃
    0.32
     Entwicklung
    0.31
    Development
    0.31
    POSITIVE LOGITS
     fulfilling
    0.33
     Unit
    0.32
     satisfying
    0.32
    ídos
    0.31
    reqParams
    0.30
    PropertyGroup
    0.30
     subunit
    0.30
     unit
    0.30
     ViewGroup
    0.30
    izou
    0.29
    Activations Density 0.005%

    No Known Activations