© 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. 107487
    Prev
    Next
    INDEX
    Explanations

    fender

    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
    2
    1.37
     I
    1.26
    من
    1.16
    </h2>
    1.13
    ，
    1.12
    3
    1.05
    </h4>
    1.05
     vilket
    1.05
    0
    0.97
    9
    0.97
    POSITIVE LOGITS
    ва
    1.43
    ла
    1.31
    a
    1.17
     ridiculed
    1.05
    ^+,
    1.03
     специали
    1.02
     март
    1.02
    า
    1.02
    സ്റ്റ്
    1.01
    dW
    1.01
    Activations Density 0.000%

    No Known Activations