© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75543
    Prev
    Next
    INDEX
    Explanations

    languages and specific terms

    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_31_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
     또
    0.21
    abis
    0.19
    กร
    0.18
    CreateWindow
    0.18
     غالب
    0.18
     –
    0.18
     constantly
    0.18
     Funktions
    0.18
    uvre
    0.18
    öffnet
    0.18
    POSITIVE LOGITS
     לאחר
    0.20
     efter
    0.19
     baada
    0.19
    ഡോ
    0.19
    恴
    0.19
     MSD
    0.19
     ensayos
    0.19
    ijiet
    0.18
    ា
    0.18
    thiophene
    0.18
    Activations Density 0.079%

    No Known Activations