© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14767
    Prev
    Next
    INDEX
    Explanations

    are followed by considered, better, very, easy, hesitant

    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_15_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
    Ồ
    0.52
    谚
    0.49
    jec
    0.42
    🇾
    0.42
    fertigt
    0.42
     विज्ञान
    0.42
     Recipe
    0.42
     Rog
    0.41
    bah
    0.41
     rebell
    0.41
    POSITIVE LOGITS
    クリスマス
    0.47
    这样的
    0.46
     adicionales
    0.43
    둘
    0.42
     dimer
    0.42
     tärke
    0.42
    .'
    0.42
    метр
    0.42
    替换
    0.41
     thema
    0.40
    Activations Density 0.024%

    No Known Activations