© 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. 98075
    Prev
    Next
    INDEX
    Explanations

    as `as many` or `as a`

    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
    legant
    0.56
    ιχ
    0.52
     ක්
    0.51
    lanelet
    0.51
    oking
    0.50
    })"
    0.50
    ighth
    0.50
    ITED
    0.50
     }:
    0.49
    tedir
    0.49
    POSITIVE LOGITS
    ア
    0.66
    ナ
    0.60
    k
    0.57
    レベル
    0.56
    ET
    0.55
    タ
    0.54
    のア
    0.53
    한
    0.53
    にも
    0.51
    デ
    0.50
    Activations Density 0.001%

    No Known Activations