© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260908
    Prev
    Next
    INDEX
    Explanations

    neotenic or retardant

    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_5_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
    1
    1.62
    0
    1.45
    The
    1.38
    า
    1.31
    ad
    1.28
     is
    1.20
    am
    1.19
    od
    1.19
     et
    1.19
     A
    1.16
    POSITIVE LOGITS
    ك
    1.17
    t
    1.12
     պ
    1.08
    ﻱ
    1.07
    ონ
    1.04
    աբ
    1.04
    ки
    1.01
    ية
    1.01
     riddled
    1.01
    }=\{
    1.00
    Activations Density 0.000%

    No Known Activations