© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 13291
    Prev
    Next
    INDEX
    Explanations

    news articles discussing political corruption and investigations

    oai_token-act-pair · gemini-2.0-flash

    Legal cases/investigations

    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
    ArgsConstructor
    -0.54
     /\.
    -0.49
    __":
    -0.47
     gainera
    -0.45
    kshake
    -0.44
    __':
    -0.43
     abused
    -0.42
    undi
    -0.42
     recent
    -0.40
     giro
    -0.39
    POSITIVE LOGITS
    MessageOf
    0.65
     **/
    
    0.64
     ویکی‌پدیای
    0.59
    phazard
    0.58
    ="@+
    0.58
    RetentionPolicy
    0.57
    borderSide
    0.57
     Rodrig
    0.54
    ]<<"
    0.54
     gynhyrchwyd
    0.52
    Activations Density 4.382%

    No Known Activations