© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96822
    Prev
    Next
    INDEX
    Explanations

    the science behind

    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_14_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
     l
    0.70
    ik
    0.52
     eyebrows
    0.52
     uk
    0.51
    flashlight
    0.51
     Razer
    0.51
     lips
    0.50
     lanyard
    0.50
     easements
    0.50
     dans
    0.50
    POSITIVE LOGITS
    {(
    0.51
     فقط
    0.49
    يمه
    0.47
     سپورت
    0.46
    }[(
    0.46
    <unused2197>
    0.46
    elevationMap
    0.46
    وع
    0.46
     indulgent
    0.46
    :(
    0.45
    Activations Density 0.041%

    No Known Activations