© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46368
    Prev
    Next
    INDEX
    Explanations

    weapon, security, legal, programming

    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_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    پ
    0.24
     faiblement
    0.21
    innest
    0.20
    ਫ਼
    0.20
    ంచరీలు
    0.20
    𒈦
    0.20
    ]}$.
    0.20
    فی
    0.19
    ارت
    0.19
     বাসন
    0.19
    POSITIVE LOGITS
    വന
    0.23
    ável
    0.22
     служ
    0.22
    BindView
    0.21
     ción
    0.21
    Trad
    0.21
     Desde
    0.20
     вчера
    0.20
     vya
    0.20
     October
    0.20
    Activations Density 0.000%

    No Known Activations