© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85813
    Prev
    Next
    INDEX
    Explanations

    entity and its attributes

    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_23_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
    icum
    0.44
     Science
    0.40
    ion
    0.39
    atan
    0.38
    Science
    0.38
    ओ
    0.38
     всех
    0.37
     obu
    0.37
     चार
    0.36
     Szent
    0.36
    POSITIVE LOGITS
    ᐈ
    0.43
     nerves
    0.43
     doorbell
    0.42
     نوع
    0.42
    mino
    0.40
     particolari
    0.40
    toadd
    0.40
     otras
    0.39
     septembre
    0.39
     být
    0.39
    Activations Density 0.001%

    No Known Activations