© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16013
    Prev
    Next
    INDEX
    Explanations

    code snippets and markup

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     كومونز
    -0.57
     OFDb
    -0.50
     CreateTagHelper
    -0.49
     simplifié
    -0.48
     HasFactory
    -0.47
    httphttps
    -0.46
    +:+
    -0.44
    #+#
    -0.44
    Посилання
    -0.43
     lenker
    -0.42
    POSITIVE LOGITS
    ressee
    0.62
    CORS
    0.61
    runge
    0.59
    vanni
    0.59
    oluene
    0.58
    latform
    0.57
    Попис
    0.56
    IANO
    0.56
    oader
    0.56
    askets
    0.54
    Activations Density 24.006%

    No Known Activations