© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21705
    Prev
    Next
    INDEX
    Explanations

    shout/scream/cry

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    大
    1.20
     big
    0.82
    big
    0.82
     大
    0.80
    Big
    0.76
     большой
    0.71
     besar
    0.71
     большие
    0.71
     대
    0.70
    ตะ
    0.70
    POSITIVE LOGITS
     shout
    1.41
     shouts
    1.18
     Shout
    1.17
     shouted
    1.05
     scream
    1.01
     shouting
    0.94
     screamed
    0.88
     screams
    0.85
     cry
    0.80
     cries
    0.79
    Activations Density 0.015%

    No Known Activations