© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30589
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    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_7_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
    ين
    0.41
     in
    0.38
     (
    0.36
     została
    0.35
    ى
    0.35
     unusable
    0.34
     sedative
    0.34
     hamstring
    0.33
     zostanie
    0.32
     outsourced
    0.32
    POSITIVE LOGITS
    2
    0.41
     be
    0.39
    be
    0.38
    3
    0.38
    :</
    0.37
    ll
    0.36
    I
    0.35
    >:
    0.33
    6
    0.32
    app
    0.32
    Activations Density 0.025%

    No Known Activations