© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41380
    Prev
    Next
    INDEX
    Explanations

    space invaders

    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_3_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
     һәм
    0.63
    Ӣ
    0.62
    .,
    0.60
    I
    0.60
     사이에
    0.59
     तरह
    0.58
     envolv
    0.55
    ท
    0.55
     tomar
    0.54
    Ⲗ
    0.54
    POSITIVE LOGITS
    ৭
    0.79
    ಿಂದ
    0.70
    categorie
    0.70
    ből
    0.70
    ள்
    0.69
    ب
    0.68
    ه
    0.66
    protection
    0.64
    predict
    0.63
    𝘀
    0.63
    Activations Density 0.002%

    No Known Activations