© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209767
    Prev
    Next
    INDEX
    Explanations

    strict necessity or requirement

    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_10_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
    ie
    1.10
    et
    1.04
    ut
    1.02
    1
    1.02
     (
    0.99
    ↵
    0.96
    .
    0.92
    The
    0.91
    For
    0.91
    ach
    0.90
    POSITIVE LOGITS
     którym
    0.90
    SleepHours
    0.88
    |।
    0.86
     ﺍ
    0.84
    که
    0.83
     sabbam
    0.83
     ګرځ
    0.83
     Букмекеры
    0.83
    ದ್ದರಿಂದ
    0.82
    miktar
    0.82
    Activations Density 0.005%

    No Known Activations