© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15005
    Prev
    Next
    INDEX
    Explanations

    you can

    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_15_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
    PropertyParam
    0.17
     hưởng
    0.17
     ભૂ
    0.16
    ervices
    0.15
     thisobject
    0.15
     oficiales
    0.14
    螟
    0.14
     セ
    0.14
     servizi
    0.14
     खिलाफ
    0.14
    POSITIVE LOGITS
     lL
    0.18
     Bays
    0.17
     nape
    0.16
     samtid
    0.16
    ash
    0.16
     Soo
    0.15
     Wor
    0.15
    šie
    0.15
     kijk
    0.15
    盃
    0.15
    Activations Density 0.029%

    No Known Activations