© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214207
    Prev
    Next
    INDEX
    Explanations

    descriptive suffixes

    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_5_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
    </h2>
    1.65
    \
    1.24
    </b>
    1.20
    </u>
    1.15
    </strong>
    1.14
    ân
    1.14
    </h3>
    1.13
     it
    1.08
    ans
    1.08
    </span>
    1.05
    POSITIVE LOGITS
    x
    1.45
    ா
    1.38
    p
    1.30
    ب
    1.24
    d
    1.23
    b
    1.23
    də
    1.21
    puri
    1.20
    ня
    1.17
    c
    1.16
    Activations Density 0.000%

    No Known Activations