© 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. 201702
    Prev
    Next
    INDEX
    Explanations

    Kemet, MTBF

    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
    و
    1.19
    n
    1.16
    l
    1.12
    u
    1.12
    ო
    1.11
    daki
    1.08
    at
    1.07
    ból
    1.06
    ו
    1.05
    U
    1.04
    POSITIVE LOGITS
    </h2>
    1.04
    </h3>
    0.98
    ân
    0.95
    </h1>
    0.95
    5
    0.91
     d
    0.86
    1
    0.84
    icht
    0.83
    igh
    0.82
     isang
    0.82
    Activations Density 0.000%

    No Known Activations