© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175436
    Prev
    Next
    INDEX
    Explanations

    `a` + descriptive adjective

    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
    ￩
    0.42
    
    0.42
    інки
    0.41
     essentially
    0.40
     whips
    0.40
    出す
    0.40
     dispensed
    0.40
     replicated
    0.39
    űt
    0.39
     വരെ
    0.39
    POSITIVE LOGITS
     "]");
    0.44
    ],
    0.43
     alignments
    0.42
    ISON
    0.42
    KeyEvent
    0.42
     ],
    0.41
    Ryan
    0.41
    玫瑰
    0.40
    F
    0.40
    IAN
    0.40
    Activations Density 0.000%

    No Known Activations