© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157307
    Prev
    Next
    INDEX
    Explanations

    sneeze

    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_2_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
    ה
    1.63
    ه
    1.43
     mortars
    1.16
     scars
    1.07
    د
    1.07
     floats
    1.06
    이랑
    1.05
     spasms
    1.04
    恹
    1.03
     étroite
    1.02
    POSITIVE LOGITS
    '
    1.77
    AR
    1.49
    0
    1.44
    na
    1.27
    اً
    1.24
    ER
    1.21
    ai
    1.20
    на
    1.09
    UR
    1.09
    at
    1.07
    Activations Density 0.000%

    No Known Activations