© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85573
    Prev
    Next
    INDEX
    Explanations

    scaling and zoom

    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_23_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
     між
    0.40
     alienation
    0.39
    Message
    0.38
     полі
    0.38
    дні
    0.38
    (_)
    0.38
    Rocks
    0.36
    expectation
    0.36
    owi
    0.35
    Sexual
    0.34
    POSITIVE LOGITS
     B
    0.45
     Q
    0.40
     Elig
    0.40
    เยี่ยม
    0.40
     отве
    0.38
     creators
    0.38
     R
    0.36
     D
    0.36
     anise
    0.36
     Huge
    0.36
    Activations Density 0.004%

    No Known Activations