© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242102
    Prev
    Next
    INDEX
    Explanations

    open GL/filename

    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
     asin
    0.41
     ChAT
    0.38
    asn
    0.38
     algebraic
    0.36
    __":
    0.36
    }\|_{
    0.35
     <<-
    0.35
     ఓ
    0.35
     Comet
    0.35
    SOCKET
    0.35
    POSITIVE LOGITS
     toi
    0.43
    panels
    0.42
    गिल
    0.42
    ロイ
    0.40
    
    0.38
     Dön
    0.38
    トゥ
    0.37
    idenza
    0.37
     Jens
    0.37
     તો
    0.36
    Activations Density 0.001%

    No Known Activations