© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2794
    Prev
    Next
    INDEX
    Explanations

    object rotation

    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_39_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
    尸
    0.22
    ètent
    0.21
    ாளையம்
    0.21
     نفرت
    0.21
    Tur
    0.21
     libel
    0.20
    ὴν
    0.20
    𒊩
    0.20
     ट्यूब
    0.20
     tubo
    0.20
    POSITIVE LOGITS
     ACT
    0.23
     DP
    0.22
     restrict
    0.20
     Expert
    0.20
     господар
    0.20
    ACT
    0.20
     z
    0.19
     rest
    0.19
     Act
    0.19
    ojana
    0.19
    Activations Density 0.018%

    No Known Activations