© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66119
    Prev
    Next
    INDEX
    Explanations

    hard to

    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_41_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
     hard
    1.84
    Hard
    1.65
    hard
    1.60
     Hard
    1.55
    硬
    1.49
    ハード
    1.44
     HARD
    1.41
     हार्ड
    1.27
    HARD
    1.24
     硬
    1.23
    POSITIVE LOGITS
     schen
    0.43
     င
    0.40
     Umgang
    0.40
     म्यू
    0.39
    甯
    0.39
     sapien
    0.39
     muc
    0.38
     llevando
    0.38
    熹
    0.38
     establishment
    0.37
    Activations Density 0.009%

    No Known Activations