© 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. 207034
    Prev
    Next
    INDEX
    Explanations

    .co domains

    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
     l
    0.25
    ca
    0.22
    ting
    0.22
     r
    0.22
     crusade
    0.21
    th
    0.20
    sa
    0.20
    na
    0.20
    umping
    0.20
    ta
    0.20
    POSITIVE LOGITS
    ي
    0.35
    هي
    0.26
    e
    0.25
    ed
    0.24
    =
    0.23
    و
    0.23
    י
    0.23
    ا
    0.22
    i
    0.21
    после
    0.21
    Activations Density 0.004%

    No Known Activations