© 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-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12268
    Prev
    Next
    INDEX
    Explanations

    the prefix "mal", often followed by a vowel and "be"

    oai_token-act-pair · gemini-2.0-flash

    mal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.99
     Roskov
    -0.98
     be
    -0.86
    IUrlHelper
    -0.85
    ].)
    -0.84
     AspNetCore
    -0.80
    setVerticalGroup
    -0.78
     Савезне
    -0.77
    extAlignment
    -0.76
     kasarigan
    -0.74
    POSITIVE LOGITS
     vertes
    0.83
     especializados
    0.82
     marins
    0.79
     hemel
    0.79
     traditionnels
    0.77
     normaux
    0.75
     automatiques
    0.75
     habet
    0.74
     classiques
    0.72
     domestiques
    0.72
    Activations Density 1.309%

    No Known Activations