© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49016
    Prev
    Next
    INDEX
    Explanations

    acknowledging

    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
    ov
    1.11
    ae
    0.96
    a
    0.95
    ac
    0.91
    ig
    0.83
    ah
    0.82
     a
    0.81
    aft
    0.79
    ud
    0.79
    inan
    0.77
    POSITIVE LOGITS
    م
    1.05
    ב
    1.00
    로
    0.98
    да
    0.94
    м
    0.94
     acknowledgement
    0.93
    the
    0.85
    מ
    0.82
     acknow
    0.81
     acknowledgment
    0.79
    Activations Density 0.024%

    No Known Activations