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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8786
    Prev
    Next
    INDEX
    Explanations

    words common in advertising and clickbait, and some words used in image file names

    oai_token-act-pair · gemini-2.0-flash

    brand/product descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     defaultstate
    -0.66
     forState
    -0.60
    apimachinery
    -0.53
    دانشنامهٔ
    -0.48
    ResumeLayout
    -0.48
     convertView
    -0.48
     Вікіпе
    -0.46
    ::~
    -0.45
    ::__
    -0.44
    AccessorTable
    -0.44
    POSITIVE LOGITS
    orghini
    0.64
    FundMe
    0.59
    amentals
    0.58
    رشف
    0.58
    dialement
    0.57
    rizona
    0.57
    athione
    0.56
    theless
    0.56
     CreateTagHelper
    0.56
    ISTRATION
    0.55
    Activations Density 14.707%

    No Known Activations