© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4567
    Prev
    Next
    INDEX
    Explanations

    list 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_40_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
     blah
    0.18
     practice
    0.16
    )))))
    0.15
     Rios
    0.15
    blah
    0.15
    yes
    0.15
    owning
    0.14
     “
    0.14
     returned
    0.14
     playing
    0.14
    POSITIVE LOGITS
    Subsec
    0.17
    ㇇
    0.17
     २
    0.17
     ²
    0.17
    ²',
    0.16
     orbifold
    0.16
    ᱒
    0.16
     १
    0.16
     COMPO
    0.16
     തവണ
    0.16
    Activations Density 0.073%

    No Known Activations