© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52227
    Prev
    Next
    INDEX
    Explanations

    Paradise Lost names

    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_31_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
     coat
    0.39
     Foundations
    0.39
    coats
    0.38
     Foundation
    0.37
     Gob
    0.37
    Foundation
    0.37
    ➔
    0.37
    ીર
    0.36
    Gob
    0.36
    foundation
    0.36
    POSITIVE LOGITS
     rn
    0.44
     المقد
    0.41
    werpen
    0.39
     smok
    0.38
    ΠΑ
    0.37
     Michelangelo
    0.37
     ∗
    0.36
    TNT
    0.36
     ευρώ
    0.35
    }}(
    0.35
    Activations Density 0.028%

    No Known Activations