© 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. 107484
    Prev
    Next
    INDEX
    Explanations

    type followed by something

    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
    t
    2.28
    r
    1.76
    m
    1.76
    l
    1.72
    n
    1.69
    la
    1.60
    p
    1.59
    er
    1.56
    il
    1.50
    an
    1.48
    POSITIVE LOGITS
    ка
    1.34
    )=
    1.25
    кает
    1.24
    cción
    1.10
    )」
    1.09
    ０
    1.09
    ০০
    1.07
    Cantidad
    1.06
    )^{[\
    1.05
    Transaksi
    1.03
    Activations Density 0.003%

    No Known Activations