© 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. 32690
    Prev
    Next
    INDEX
    Explanations

    move beyond

    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
     moved
    0.48
    moved
    0.44
    に移
    0.41
     gravitate
    0.39
     move
    0.39
     reinforce
    0.37
     boil
    0.37
    移
    0.37
    tem
    0.36
     cranes
    0.36
    POSITIVE LOGITS
     kebut
    0.40
     discarding
    0.38
    PRS
    0.38
     remplacement
    0.37
     Op
    0.37
     ব্যপারে
    0.37
    +)
    0.35
    cerning
    0.35
    proxy
    0.35
     bỏ
    0.35
    Activations Density 0.011%

    No Known Activations