© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199838
    Prev
    Next
    INDEX
    Explanations

    expectations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    Discrimin
    0.40
    MEAS
    0.39
     proporción
    0.38
     इच्छुक
    0.38
    幅度
    0.37
    仴
    0.36
     মদ
    0.36
    𝗗
    0.36
    лость
    0.35
    magnitude
    0.35
    POSITIVE LOGITS
     standards
    0.53
     expectations
    0.52
     needs
    0.47
     peculiarities
    0.46
    ifications
    0.46
    ilen
    0.45
    uali
    0.45
     cares
    0.44
     prescriptions
    0.42
    aken
    0.42
    Activations Density 0.004%

    No Known Activations