© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56864
    Prev
    Next
    INDEX
    Explanations

    astronomy observations

    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_11_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
    со
    0.55
    Escolhido
    0.55
    verso
    0.53
    ু
    0.51
     मुताब
    0.50
    :
    0.50
    িয়াম
    0.48
    ром
    0.48
    necklace
    0.48
    ‌,
    0.48
    POSITIVE LOGITS
    ă
    0.60
    x
    0.59
     N
    0.58
    ācijas
    0.58
    ările
    0.55
    ės
    0.54
    㓦
    0.54
     আই
    0.54
    ări
    0.54
     הנ
    0.53
    Activations Density 0.009%

    No Known Activations