© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5055
    Prev
    Next
    INDEX
    Explanations

    topics involving finances, especially related to how they are influenced by government or corporations

    oai_token-act-pair · gemini-2.0-flash

    Funding/grants

    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
    >[]
    -0.49
    ConnectionState
    -0.47
     bArr
    -0.46
    }();
    -0.45
     Funding
    -0.45
     func
    -0.45
     MusicBrainz
    -0.44
     inhibitors
    -0.44
    eter
    -0.44
    toje
    -0.43
    POSITIVE LOGITS
    setVerticalGroup
    0.85
    Jeografia
    0.76
     صوتيه
    0.71
    !*\
    0.68
     propOrder
    0.66
    aarrggbb
    0.65
    новништво
    0.65
     '\\;'
    0.65
     autorytatywna
    0.64
     ModelExpression
    0.63
    Activations Density 2.111%

    No Known Activations