© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132438
    Prev
    Next
    INDEX
    Explanations

    crime, cancer, diabetes, gun violence prevention

    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_1_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
    K
    1.41
    3
    1.25
                
    1.20
    )
    1.16
    س
    1.15
    는
    1.11
     to
    1.10
     that
    1.10
    1.09
    }
    1.07
    POSITIVE LOGITS
    ᇂ
    1.20
     наличи
    1.13
     effectuées
    1.09
    orems
    1.00
    ’
    1.00
    톄
    0.98
    tions
    0.98
    dı
    0.98
    婇
    0.96
     mobili
    0.95
    Activations Density 0.001%

    No Known Activations