© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53429
    Prev
    Next
    INDEX
    Explanations

    apollo missions

    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_31_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
    ःख
    0.33
    ølge
    0.31
     $@
    0.30
    وء
    0.30
     spanned
    0.29
    倬
    0.29
    isPreview
    0.28
     ভয়ঙ্কর
    0.28
    綜
    0.28
    ྥ
    0.28
    POSITIVE LOGITS
    電
    0.32
     Manish
    0.32
     Dant
    0.32
     adm
    0.31
     Mathis
    0.30
     elec
    0.30
     உதய
    0.29
     điện
    0.29
     elektro
    0.28
     logins
    0.28
    Activations Density 0.015%

    No Known Activations