© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28053
    Prev
    Next
    INDEX
    Explanations

    menu or materials

    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_40_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
    ’
    0.47
    <0x19>
    0.47
    swear
    0.44
    த்ரே
    0.42
    '
    0.42
     Diagn
    0.41
     pascal
    0.39
    ustes
    0.38
     healers
    0.37
    സിൽ
    0.36
    POSITIVE LOGITS
    ysteem
    0.39
    জন
    0.38
    Neder
    0.38
    Ń
    0.37
     مردم
    0.36
    umption
    0.36
    mith
    0.35
    တို့
    0.35
    ماية
    0.35
     žmog
    0.35
    Activations Density 0.004%

    No Known Activations