© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161892
    Prev
    Next
    INDEX
    Explanations

    vitalik.eth or ic

    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_2_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
    드의
    1.22
    א
    1.13
     ejecutar
    1.11
     revêtu
    1.09
    ų
    1.08
     quét
    1.07
     acceder
    1.05
     térm
    1.04
     concomitant
    1.02
     desenvolver
    1.02
    POSITIVE LOGITS
    s
    2.77
    y
    1.59
    س
    1.49
    1
    1.48
    a
    1.45
    d
    1.36
    с
    1.35
    स
    1.30
    3
    1.29
    se
    1.23
    Activations Density 0.000%

    No Known Activations