© 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. 61444
    Prev
    Next
    INDEX
    Explanations

    PRINCE, in, brin, brinjal

    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
    ى
    1.31
    ал
    1.30
    い
    1.30
    า
    1.27
    ี
    1.27
    та
    1.24
    ik
    1.17
    ী
    1.17
    ש
    1.16
    )，
    1.14
    POSITIVE LOGITS
     I
    1.25
    t
    1.20
     is
    1.09
    k
    0.98
    l
    0.96
     confir
    0.94
    g
    0.88
     hypothesized
    0.87
    ział
    0.82
    d
    0.81
    Activations Density 0.000%

    No Known Activations