© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 250996
    Prev
    Next
    INDEX
    Explanations

    worsening conditions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     f
    0.68
     ف
    0.48
     ฟ
    0.45
     reworked
    0.44
     फ
    0.43
     edited
    0.42
     maintained
    0.42
     altered
    0.41
    ฟ
    0.41
     remodeled
    0.38
    POSITIVE LOGITS
    Sou
    0.46
     Sou
    0.44
     encouraged
    0.43
    single
    0.42
     shocked
    0.42
     surprised
    0.42
     startled
    0.42
    sou
    0.41
    reach
    0.40
    Hit
    0.40
    Activations Density 0.001%

    No Known Activations