© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216502
    Prev
    Next
    INDEX
    Explanations

    Craigslist, Gumtree, classifieds

    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_31_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
     দীপ
    0.45
     oppression
    0.41
     é
    0.40
    ടിക്ക
    0.40
     remainder
    0.39
     concomit
    0.38
     Plank
    0.38
     conduct
    0.38
     shower
    0.37
    ression
    0.37
    POSITIVE LOGITS
    ྔ
    0.44
    邋
    0.42
    फोल
    0.41
    otides
    0.39
    Excuse
    0.39
    ทร
    0.39
    уз
    0.39
    Exterior
    0.39
    mylist
    0.39
     propri
    0.38
    Activations Density 0.000%

    No Known Activations