© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176585
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives followed by 'than' or 'enough'

    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_24_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
     মুক্ত
    0.44
    揚
    0.41
    тента
    0.40
     Kauf
    0.39
    텐
    0.39
     Scope
    0.38
     المشار
    0.38
     entera
    0.38
     लाइब्रेरी
    0.38
    形の
    0.37
    POSITIVE LOGITS
    ⑫
    0.40
     stratified
    0.39
     Jazeera
    0.38
     prime
    0.38
    㴌
    0.38
    ús
    0.37
    levelup
    0.37
     rm
    0.37
    mii
    0.36
     partially
    0.36
    Activations Density 0.005%

    No Known Activations