© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14940
    Prev
    Next
    INDEX
    Explanations

    uppercase letters and the characters that commonly follow them

    oai_token-act-pair · gemini-2.0-flash

    "V"

    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
     EconPapers
    -0.64
     autorytatywna
    -0.64
    SourceChecksum
    -0.63
     OFDb
    -0.62
    ритори
    -0.51
     ddelweddau
    -0.50
    SharedDtor
    -0.50
    AddTagHelper
    -0.50
    IsMutable
    -0.50
    StoryboardSegue
    -0.50
    POSITIVE LOGITS
    EP
    0.68
    PE
    0.67
    AME
    0.66
    ORT
    0.66
    ende
    0.64
    OTT
    0.63
    lès
    0.62
    PV
    0.60
    OVE
    0.60
    AX
    0.60
    Activations Density 32.669%

    No Known Activations