© 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. 39772
    Prev
    Next
    INDEX
    Explanations

    assume

    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
    ↵
    0.67
     I
    0.67
    </h3>
    0.63
            
    0.55
    </b>
    0.54
         
    0.51
    </h1>
    0.51
    "-
    0.47
    I
    0.46
    </td>
    0.45
    POSITIVE LOGITS
    ၅
    0.67
    awać
    0.59
    တတ်
    0.58
    ﻒ
    0.58
    လိုအပ်
    0.57
    使う
    0.57
    at
    0.56
     commencer
    0.55
     Фургала
    0.55
     වලින්
    0.54
    Activations Density 0.012%

    No Known Activations