© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80798
    Prev
    Next
    INDEX
    Explanations

    respond as

    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_0_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
     drugih
    1.36
    ме
    1.34
    ᱘
    1.27
    8
    1.26
    。,
    1.25
    。
    1.23
    ༦
    1.23
     homage
    1.23
    ၈
    1.23
    на
    1.22
    POSITIVE LOGITS
    t
    1.58
    u
    1.51
    i
    1.49
    l
    1.48
    h
    1.37
    dehyde
    1.29
    td
    1.23
    m
    1.23
    로
    1.23
    ts
    1.18
    Activations Density 0.008%

    No Known Activations