© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57339
    Prev
    Next
    INDEX
    Explanations

    let down

    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_11_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
    ன்
    0.60
    ional
    0.59
    现象
    0.57
    rs
    0.56
    rx
    0.56
    ic
    0.56
    <0x91>
    0.55
    rd
    0.55
     mecánica
    0.55
     about
    0.54
    POSITIVE LOGITS
    ोगे
    0.57
    Oke
    0.55
     বিষয়
    0.54
    WriteLine
    0.53
    TextMesh
    0.52
    Pessoal
    0.52
     pate
    0.51
    Pole
    0.51
     occupiers
    0.50
    Gli
    0.50
    Activations Density 0.000%

    No Known Activations