© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202475
    Prev
    Next
    INDEX
    Explanations

    about following URLs

    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_37_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
     empêcher
    0.43
    चानक
    0.41
    फिया
    0.40
     subcluster
    0.40
    motionProxy
    0.40
     numerose
    0.40
    我自己
    0.39
    徝
    0.39
     myself
    0.38
     देम
    0.38
    POSITIVE LOGITS
    Client
    0.46
     Client
    0.46
     company
    0.45
     client
    0.44
     Company
    0.44
     Biography
    0.43
     Organization
    0.43
    Company
    0.42
     clients
    0.41
    E
    0.40
    Activations Density 0.000%

    No Known Activations