© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139784
    Prev
    Next
    INDEX
    Explanations

    quinones, turntables, disease, cart

    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_12_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
    :
    0.54
    felter
    0.50
    ó
    0.50
    icosa
    0.49
    ‬
    0.49
    )
    0.48
    é
    0.48
    feld
    0.47
     "
    0.46
    jeto
    0.46
    POSITIVE LOGITS
    Bangladesh
    0.59
    বাংলাদেশ
    0.57
    eksiyon
    0.57
    畩
    0.56
    Như
    0.54
     Mahabhar
    0.54
     പിന്തുണ
    0.53
    Спо
    0.52
    После
    0.51
     Ancak
    0.51
    Activations Density 0.001%

    No Known Activations