© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126082
    Prev
    Next
    INDEX
    Explanations

    random generation

    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_3_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
    к
    0.85
    }]
    0.77
    p
    0.70
    ק
    0.69
    immunity
    0.68
    р
    0.67
    v
    0.66
    },
    0.65
    ്
    0.63
    q
    0.61
    POSITIVE LOGITS
    re
    0.71
     midline
    0.63
     i
    0.62
     autopilot
    0.62
     creo
    0.61
     brainstorm
    0.61
    이다
    0.61
    ור
    0.60
     ranc
    0.59
     creer
    0.59
    Activations Density 0.004%

    No Known Activations