© 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. 12580
    Prev
    Next
    INDEX
    Explanations

    I followed by verbs of belief or knowledge

    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
    ྗ
    0.37
    IGE
    0.36
     PS
    0.35
     научной
    0.34
    钰
    0.34
     EdgeInsets
    0.34
    compression
    0.34
    től
    0.34
    棱
    0.34
     Genres
    0.34
    POSITIVE LOGITS
     preposition
    0.37
    flo
    0.36
     ac
    0.36
    ঐ
    0.36
     handicapped
    0.35
     fa
    0.35
     flood
    0.35
     shades
    0.34
    stens
    0.34
     overflows
    0.34
    Activations Density 0.051%

    No Known Activations