© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116643
    Prev
    Next
    INDEX
    Explanations

    sequences after separators

    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_27_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
    Ѡ
    0.26
    вач
    0.21
     chromatographed
    0.20
    浱
    0.20
     доступны
    0.20
     балан
    0.20
    Borderless
    0.20
     famílias
    0.20
    炭
    0.19
    QTTR
    0.19
    POSITIVE LOGITS
     member
    0.21
     investing
    0.21
    yes
    0.21
     curator
    0.21
     items
    0.20
     environment
    0.20
     multitasking
    0.20
     build
    0.20
     saying
    0.20
     számára
    0.20
    Activations Density 0.004%

    No Known Activations