© 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. 49538
    Prev
    Next
    INDEX
    Explanations

    wagon wheel, boarding, train

    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
    k
    1.16
    se
    0.98
    of
    0.98
    ene
    0.98
    c
    0.95
    ere
    0.90
    ess
    0.89
    ch
    0.88
    ä
    0.88
    ya
    0.86
    POSITIVE LOGITS
    𝘁
    0.88
    Ⴀ
    0.81
    AT
    0.79
    াৰ
    0.79
    ্ঞ
    0.78
     significativas
    0.77
    Ⴌ
    0.76
     AVAudio
    0.75
    古い
    0.75
     administrativas
    0.74
    Activations Density 0.006%

    No Known Activations