© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210642
    Prev
    Next
    INDEX
    Explanations

    in my opinion

    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_20_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
     atof
    0.19
    updateOne
    0.18
    Ꮼ
    0.18
    വിന്റെ
    0.17
     operandSize
    0.17
     вла
    0.17
     اچھی
    0.17
     précisément
    0.17
     limiting
    0.17
    >(_
    0.17
    POSITIVE LOGITS
    km
    0.22
    hdad
    0.21
     चुप
    0.21
    duit
    0.20
    atures
    0.20
    iada
    0.20
    lla
    0.19
     seem
    0.19
     enigmatic
    0.19
     nervioso
    0.19
    Activations Density 0.000%

    No Known Activations