© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 150739
    Prev
    Next
    INDEX
    Explanations

    list item number

    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_18_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
     im
    0.55
     transmission
    0.55
    ’
    0.55
     set
    0.54
     custom
    0.53
     server
    0.51
     condenser
    0.51
    igu
    0.51
     fence
    0.51
    +
    0.51
    POSITIVE LOGITS
     महाराष्ट्रा
    0.58
    تاریخ
    0.54
    Ş
    0.54
    Università
    0.53
    ভারতীয়
    0.52
    ﮐ
    0.51
    䡏
    0.51
     Акча
    0.50
     Jako
    0.50
    Hindi
    0.50
    Activations Density 0.010%

    No Known Activations