© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101530
    Prev
    Next
    INDEX
    Explanations

    public works

    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_14_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
     Tentang
    0.55
    တ
    0.55
    유
    0.53
     textSize
    0.52
    ሆኑ
    0.52
    otras
    0.52
    رض
    0.51
    祂
    0.51
     Австра
    0.49
    وضع
    0.49
    POSITIVE LOGITS
    ızı
    0.58
    m
    0.55
    g
    0.55
    𝑝
    0.53
    es
    0.52
    izing
    0.50
    ség
    0.46
    ikap
    0.46
    वाद
    0.46
    idikan
    0.46
    Activations Density 0.000%

    No Known Activations