© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193649
    Prev
    Next
    INDEX
    Explanations

    can perform, handle, use

    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_27_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
     Juris
    0.38
    spider
    0.38
    вью
    0.38
     Ansprüche
    0.37
    middleware
    0.37
    فو
    0.37
    lovl
    0.36
    檤
    0.36
     Directive
    0.36
    fov
    0.36
    POSITIVE LOGITS
     roofing
    0.37
    lications
    0.37
    Modern
    0.36
     alarmed
    0.36
     attire
    0.36
    RuL
    0.36
    Morgan
    0.35
    Best
    0.35
     adept
    0.35
     attracting
    0.34
    Activations Density 0.005%

    No Known Activations