© 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. 57819
    Prev
    Next
    INDEX
    Explanations

    what's possible

    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
    К
    0.64
    ನಾಡ
    0.64
     catastrophes
    0.63
     परन्तु
    0.61
     [...]
    0.59
     использование
    0.59
    ي
    0.59
     composers
    0.58
     किंतु
    0.58
     setups
    0.58
    POSITIVE LOGITS
    s
    0.75
    3
    0.65
    wedge
    0.55
    ς
    0.52
    ారీ
    0.52
    りたい
    0.52
     frutto
    0.50
    AGON
    0.50
    ALL
    0.49
    polymer
    0.49
    Activations Density 0.001%

    No Known Activations