© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19196
    Prev
    Next
    INDEX
    Explanations

    providing or performing actions

    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_15_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
    ีย
    0.23
    フ
    0.21
    拉
    0.20
    нта
    0.20
     innovating
    0.20
    llä
    0.19
     अशा
    0.19
    ᅦ
    0.19
    на
    0.19
    വധി
    0.19
    POSITIVE LOGITS
     വ്യക്ത
    0.23
    ணர்வு
    0.22
     स्पष्ट
    0.21
    igste
    0.21
     தொடர்பாக
    0.21
     பின்பற்ற
    0.20
    
    0.20
    则是
    0.20
     فإن
    0.20
     Exercise
    0.20
    Activations Density 0.098%

    No Known Activations