© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158474
    Prev
    Next
    INDEX
    Explanations

    feigned + emotion/action

    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_2_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
    is
    1.45
    el
    1.36
    a
    1.33
    é
    1.26
    um
    1.13
    et
    1.10
    ires
    1.04
    p
    1.03
    ethe
    0.96
    ation
    0.95
    POSITIVE LOGITS
    Т
    1.55
    ح
    1.53
    ка
    1.49
    ש
    1.48
    ك
    1.46
    К
    1.44
    О
    1.43
    ために
    1.41
    ক
    1.40
    Я
    1.38
    Activations Density 0.001%

    No Known Activations