© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2367
    Prev
    Next
    INDEX
    Explanations

    technical business metrics focused on customers and claims

    oai_token-act-pair · gemini-2.0-flash

    claims

    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
     claim
    -3.38
     claims
    -3.20
     Claim
    -3.19
     Claims
    -3.06
     claimed
    -3.06
    Claim
    -3.03
     CLAIM
    -2.98
    claim
    -2.94
     claiming
    -2.94
    claims
    -2.91
    POSITIVE LOGITS
    astify
    0.57
    ISupport
    0.45
     adaptés
    0.40
    HostException
    0.40
    เภ
    0.39
     hindrance
    0.39
     виправивши
    0.38
     refrigerators
    0.38
     Dernière
    0.38
     Turnpike
    0.38
    Activations Density 3.790%

    No Known Activations