© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68790
    Prev
    Next
    INDEX
    Explanations

    accretion disk formation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     c
    0.51
     inter
    0.48
     Inter
    0.45
     t
    0.44
     ten
    0.43
     NE
    0.42
     Ko
    0.42
    imide
    0.41
     Compos
    0.41
     K
    0.40
    POSITIVE LOGITS
     ক্রয়
    0.39
    Mua
    0.39
    agena
    0.38
    querysearch
    0.38
    altered
    0.38
    PPtr
    0.38
     場
    0.37
    Venue
    0.37
    💴
    0.37
    Hozzáférés
    0.37
    Activations Density 0.002%

    No Known Activations