© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43250
    Prev
    Next
    INDEX
    Explanations

    the following

    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
    Not in Any Lists

    No Comments

    Negative Logits
    😓
    0.12
    🤤
    0.12
    lapping
    0.12
    😑
    0.11
    तत्
    0.11
    මු
    0.11
     Bany
    0.11
    ையாக
    0.11
    ذی
    0.11
    ථ
    0.11
    POSITIVE LOGITS
     veteran
    0.11
     researchers
    0.11
     experiences
    0.11
     Austin
    0.10
     media
    0.10
    ía
    0.10
     neuro
    0.10
     lawmakers
    0.10
     website
    0.10
     Experiences
    0.10
    Activations Density 0.098%

    No Known Activations