© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14306
    Prev
    Next
    INDEX
    Explanations

    verbs ending in 'ed'

    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_13_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
    ตาม
    0.22
     somebody
    0.22
     ตาม
    0.22
    ólnie
    0.21
     iemand
    0.20
     একজন
    0.20
     ผ
    0.19
     mind
    0.19
     воспита
    0.19
    På
    0.19
    POSITIVE LOGITS
     அமைந்துள்ளது
    0.22
    にくい
    0.21
    </h2>
    0.20
    に含ま
    0.20
    忑
    0.20
     de
    0.20
     싫
    0.20
     landscapes
    0.20
     territoires
    0.19
     rapides
    0.19
    Activations Density 0.018%

    No Known Activations