© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79520
    Prev
    Next
    INDEX
    Explanations

    sounds like

    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
    .
    1.94
    ۔
    1.09
    но
    1.07
    。
    1.05
    érc
    1.04
    ٣
    1.04
    ्य
    1.03
    يل
    1.03
    soldiers
    1.02
    ция
    1.02
    POSITIVE LOGITS
     and
    1.80
    0
    1.76
     or
    1.61
    The
    1.58
    A
    1.46
    ۰
    1.40
     The
    1.32
     in
    1.21
    اب
    1.21
    ینگ
    1.20
    Activations Density 0.001%

    No Known Activations