© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202974
    Prev
    Next
    INDEX
    Explanations

    experience the [adjective]

    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_6_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
    м
    1.13
    م
    1.13
    is
    1.03
    n
    1.02
    um
    0.95
    ৬
    0.95
    1
    0.89
    𝟏
    0.88
    ت
    0.87
    س
    0.86
    POSITIVE LOGITS
    ’
    0.85
    ’),
    0.84
     корм
    0.83
     arrhyth
    0.82
     перевоз
    0.82
     arrhythmias
    0.82
     πολλ
    0.82
     взаимо
    0.81
     велосипе
    0.80
     ос
    0.80
    Activations Density 0.001%

    No Known Activations