© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83746
    Prev
    Next
    INDEX
    Explanations

    ignoring requests, people, or things

    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_0_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
    يا
    1.91
    д
    1.88
    дный
    1.52
     aérea
    1.48
     efectivo
    1.44
     amplio
    1.41
    يل
    1.36
    دين
    1.34
     ahorro
    1.34
    其他
    1.33
    POSITIVE LOGITS
    t
    2.61
    r
    2.50
    y
    2.13
    the
    2.06
    s
    2.02
    kan
    1.97
    _
    1.88
    er
    1.82
    z
    1.82
    ties
    1.80
    Activations Density 0.002%

    No Known Activations