© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91318
    Prev
    Next
    INDEX
    Explanations

    desire to/for

    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
    oribus
    0.68
    𝚑
    0.66
    𝗳
    0.66
    书法
    0.64
     Cnemidophorus
    0.63
    𝗵
    0.62
    𝙛
    0.60
    hitva
    0.60
    kfollowers
    0.60
     चिकित्सक
    0.59
    POSITIVE LOGITS
     e
    0.77
    .
    0.68
    one
    0.64
    i
    0.64
     eller
    0.62
     alebo
    0.60
     sparen
    0.60
     v
    0.59
     specs
    0.59
    י
    0.59
    Activations Density 0.007%

    No Known Activations