© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5762
    Prev
    Next
    INDEX
    Explanations

    short phrases including the words "there", "is", and connecting words like "and" and "with."

    oai_token-act-pair · gemini-2.0-flash

    Reviews

    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
     Amenities
    -0.84
     Facilities
    -0.80
     Facility
    -0.80
     FACILITY
    -0.77
    Facility
    -0.77
     amenity
    -0.77
    facilities
    -0.77
     FACILITIES
    -0.75
    Facilities
    -0.72
    Amenities
    -0.71
    POSITIVE LOGITS
    XmlAccessType
    0.63
     intptr
    0.60
    \{\\
    0.59
    UnsafeEnabled
    0.59
    حوالہ
    0.59
    Obrázky
    0.56
    Salta
    0.55
    endwhile
    0.55
    ViewImports
    0.51
     iconFacebook
    0.51
    Activations Density 6.637%

    No Known Activations