© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8201
    Prev
    Next
    INDEX
    Explanations

    cease and desist

    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
     bicovariant
    0.24
     MaxPooling
    0.23
    活着
    0.22
    𒅎
    0.22
     cosm
    0.22
    litz
    0.21
    👼
    0.21
    侃
    0.21
     Estable
    0.21
     mottled
    0.21
    POSITIVE LOGITS
    Christ
    0.26
    オー
    0.25
    Metro
    0.24
     கிறிஸ்து
    0.24
     Christ
    0.24
    metro
    0.24
     '(
    0.24
    Aye
    0.23
     Metro
    0.23
     Christophe
    0.22
    Activations Density 0.000%

    No Known Activations