© 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. 8162
    Prev
    Next
    INDEX
    Explanations

    terminal or PowerShell

    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
    软件
    0.18
    ólogos
    0.18
     sair
    0.17
     firebase
    0.17
     |=
    0.17
    Software
    0.17
     Software
    0.16
     Violence
    0.16
    धारक
    0.16
     software
    0.16
    POSITIVE LOGITS
     instances
    0.25
    InstanceOf
    0.22
    instances
    0.21
     Instances
    0.21
     Ne
    0.20
     Ching
    0.20
     možno
    0.18
     ሙ
    0.18
     Instance
    0.18
    Ne
    0.17
    Activations Density 0.089%

    No Known Activations