© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172357
    Prev
    Next
    INDEX
    Explanations

    release of prisoners and hostages

    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_20_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
    Relationships
    0.46
    relationship
    0.46
     कदम
    0.45
    县
    0.45
    Conflicts
    0.45
    Relationship
    0.44
    に基づいて
    0.44
     Relationships
    0.43
     مسی
    0.43
    StringTo
    0.41
    POSITIVE LOGITS
     melts
    0.45
    콜
    0.45
    нтов
    0.44
    ⏟
    0.42
     cloak
    0.41
    otroph
    0.41
    !?
    0.41
    ált
    0.41
    ாப்
    0.41
    ❗
    0.41
    Activations Density 0.001%

    No Known Activations