© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 150028
    Prev
    Next
    INDEX
    Explanations

    The Guardian articles

    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_18_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
    ulsory
    0.48
    ቶች
    0.46
     아니
    0.46
     스토리
    0.45
    ਤ
    0.45
    ریت
    0.43
    bursement
    0.42
     Eds
    0.42
     تش
    0.42
     폴
    0.42
    POSITIVE LOGITS
     healer
    0.47
    Dit
    0.46
     twee
    0.46
     rampage
    0.45
     boxed
    0.45
    Ketika
    0.44
    ৰ
    0.44
    FR
    0.43
    Buffalo
    0.43
    }.\
    0.42
    Activations Density 0.000%

    No Known Activations