© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206810
    Prev
    Next
    INDEX
    Explanations

    right angles

    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_20_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
    Smartphone
    0.17
    Joyce
    0.17
     Joyce
    0.17
    нент
    0.16
     reviews
    0.15
     å
    0.15
     ketiga
    0.15
     ajt
    0.15
     اپنی
    0.15
     voicemail
    0.15
    POSITIVE LOGITS
    other
    0.17
    ola
    0.16
    koľ
    0.16
    users
    0.15
     bulunan
    0.15
    ட்சத்திர
    0.15
    毘
    0.15
    linux
    0.15
     Indic
    0.15
     Ra
    0.15
    Activations Density 0.001%

    No Known Activations