© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172380
    Prev
    Next
    INDEX
    Explanations

    will be

    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_20_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
     perish
    0.40
     Curtain
    0.38
     reject
    0.37
    煅
    0.37
     করছি
    0.37
     continue
    0.36
     explicitly
    0.36
     deny
    0.36
     veil
    0.36
     Northern
    0.36
    POSITIVE LOGITS
     със
    0.46
    ຖືກ
    0.43
     velič
    0.43
     Ге
    0.42
    ˋ
    0.42
    VertexBuffer
    0.41
     Buttons
    0.41
    MOTOR
    0.41
    inputFields
    0.40
    ższej
    0.40
    Activations Density 0.000%

    No Known Activations