© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3237
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers alongside building-related words and prepositions.

    oai_token-act-pair · gemini-2.0-flash

    rooms and buildings

    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
     room
    -0.75
     bedroom
    -0.71
    ursales
    -0.68
    IndentedString
    -0.66
    room
    -0.64
     Room
    -0.64
    ]),
    -0.63
    __":
    -0.63
     Wohnung
    -0.63
     linkovi
    -0.62
    POSITIVE LOGITS
     base
    0.56
    ėjimo
    0.56
    bcrypt
    0.50
    setPointSize
    0.46
     plant
    0.46
    Kjelder
    0.45
     sta
    0.44
    ews
    0.44
     ball
    0.43
    plugin
    0.43
    Activations Density 2.940%

    No Known Activations