© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66473
    Prev
    Next
    INDEX
    Explanations

    earthquake magnitude

    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_41_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
     థ
    0.41
    បទ
    0.38
    恂
    0.36
    了解到
    0.36
    BUILD
    0.35
     penetrating
    0.35
    मिथ
    0.35
    )+(
    0.34
    occupied
    0.34
     hippocamp
    0.34
    POSITIVE LOGITS
     measure
    0.53
     mesures
    0.51
     measures
    0.51
     ML
    0.51
     m
    0.50
     magnitude
    0.50
     magnitudes
    0.50
     mesure
    0.49
    ML
    0.48
     må
    0.48
    Activations Density 0.002%

    No Known Activations