© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76457
    Prev
    Next
    INDEX
    Explanations

    costs (marketing, training, transfer)

    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_31_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
     schedule
    0.38
    瞋
    0.37
     Liberation
    0.37
     Income
    0.36
     비용
    0.36
     Culture
    0.36
     Hungry
    0.36
     తల్లి
    0.36
     wis
    0.35
     Schedule
    0.35
    POSITIVE LOGITS
    ाब
    0.39
    Rober
    0.39
    剥
    0.38
    ச்சை
    0.37
    ESPN
    0.37
    Ghost
    0.37
     ROBERT
    0.36
    bation
    0.36
    离婚
    0.36
    Bankruptcy
    0.36
    Activations Density 0.008%

    No Known Activations