© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 210232
    Prev
    Next
    INDEX
    Explanations

    sounds of distress

    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_43_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
     blink
    0.45
    臨
    0.42
     Flemish
    0.42
     সেসব
    0.38
    फेक्शन
    0.38
    សុ
    0.37
    bona
    0.37
     pigmented
    0.37
     secular
    0.36
     conditional
    0.36
    POSITIVE LOGITS
     howling
    1.43
     howl
    1.24
     screaming
    0.98
     whining
    0.91
     screams
    0.87
     scream
    0.86
    嚎
    0.85
     screamed
    0.84
     whine
    0.80
    呜
    0.77
    Activations Density 0.002%

    No Known Activations