© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201224
    Prev
    Next
    INDEX
    Explanations

    diaper rash cream

    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_12_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
    ogh
    0.44
    imb
    0.43
    ∼
    0.41
    astricht
    0.41
    ଲ
    0.40
     నిర్ణ
    0.40
    agg
    0.39
    agiri
    0.39
    的基础上
    0.38
    ])
    0.38
    POSITIVE LOGITS
     MOT
    0.47
     Puede
    0.46
    MOT
    0.44
     Mot
    0.42
    BC
    0.42
    钰
    0.42
     hidrógeno
    0.41
     Instit
    0.41
    Containing
    0.41
    рина
    0.41
    Activations Density 0.000%

    No Known Activations