© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206428
    Prev
    Next
    INDEX
    Explanations

    Proof-of-Stake (PoS)

    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_6_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
    та
    0.98
    是
    0.93
     việc
    0.93
    са
    0.90
    σ
    0.86
    рга
    0.83
    on
    0.83
    ба
    0.82
     porch
    0.81
     fiscale
    0.79
    POSITIVE LOGITS
    ل
    1.09
    lm
    0.98
    ljeni
    0.94
    lere
    0.92
    lc
    0.91
    lara
    0.89
    los
    0.89
    Đ
    0.89
    lje
    0.85
     Banyak
    0.84
    Activations Density 0.000%

    No Known Activations