© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8272
    Prev
    Next
    INDEX
    Explanations

    mentions of professional, medical and real-estate services

    oai_token-act-pair · gemini-2.0-flash

    Describing services or qualifications

    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
     AssemblyCulture
    -0.81
     CreateTagHelper
    -0.68
    liar
    -0.49
    displayquote
    -0.46
    le
    -0.46
     certification
    -0.46
    $_['
    -0.46
    TintMode
    -0.45
    EnumMember
    -0.44
    #+#
    -0.44
    POSITIVE LOGITS
    ArrowToggle
    0.80
    AsUp
    0.68
     raiſ
    0.65
    InjectAttribute
    0.65
     fekete
    0.59
     Ause
    0.57
     hand
    0.56
    ]--;
    0.56
     Hand
    0.55
    Hand
    0.54
    Activations Density 6.554%

    No Known Activations