© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29140
    Prev
    Next
    INDEX
    Explanations

    little followed by descriptive words

    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_10_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
    }&
    0.44
    .​
    0.44
     பாதிக்கப்பட்ட
    0.44
    nd
    0.43
    tiempo
    0.43
    nt
    0.41
    t
    0.41
    𒋗
    0.40
    什么
    0.40
    実際の
    0.39
    POSITIVE LOGITS
    ו
    0.47
     erine
    0.46
    ও
    0.46
    но
    0.45
    G
    0.44
     notre
    0.44
    ER
    0.42
    0.42
    L
    0.42
     superpower
    0.41
    Activations Density 0.011%

    No Known Activations