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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5461
    Prev
    Next
    INDEX
    Explanations

    words and phrases that refer to journeys or paths, both literal and metaphorical.

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    เอง
    -0.62
    #
    -0.62
    AddTagHelper
    -0.62
     BoxFit
    -0.60
     Himself
    -0.57
    xffffff
    -0.56
    rungsseite
    -0.54
    xFFFFFF
    -0.53
    queryInterface
    -0.53
    selves
    -0.52
    POSITIVE LOGITS
     your
    1.29
     seu
    1.16
     seus
    1.15
     sua
    1.07
     her
    1.05
     their
    1.05
     suas
    1.04
     своих
    1.01
     his
    1.00
     ihrer
    1.00
    Activations Density 2.186%

    No Known Activations