© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13424
    Prev
    Next
    INDEX
    Explanations

    language related to legal and financial status and protection thereof

    oai_token-act-pair · gemini-2.0-flash

    legal/economic matters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     betyd
    -0.60
     amanhã
    -0.57
     goutte
    -0.56
     Zuw
    -0.55
     llorar
    -0.55
    ício
    -0.54
    /***/
    -0.54
     optique
    -0.53
    TestingModule
    -0.53
     idée
    -0.53
    POSITIVE LOGITS
    <bos>
    0.68
    ".
    0.68
     Roskov
    0.68
    gameserver
    0.68
    '),
    0.65
    '},
    0.65
     InputDecoration
    0.64
    Havolalar
    0.61
    '],$
    0.60
    `,
    0.59
    Activations Density 2.019%

    No Known Activations