© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92920
    Prev
    Next
    INDEX
    Explanations

    silence followed by descriptive verbs

    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_11_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
    2
    0.65
     Risk
    0.64
     risk
    0.61
     RISK
    0.60
     APP
    0.59
     price
    0.58
     review
    0.58
     pick
    0.58
     threat
    0.58
    ]
    0.58
    POSITIVE LOGITS
    फ
    0.56
    antiene
    0.52
    is
    0.52
    =\
    0.52
    dequeue
    0.52
    ف
    0.52
    椿
    0.51
    os
    0.50
     freien
    0.50
    ўнай
    0.50
    Activations Density 0.003%

    No Known Activations