© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11027
    Prev
    Next
    INDEX
    Explanations

    shortened versions of "it is" and "I have"

    oai_token-act-pair · gemini-2.0-flash

    its

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    its
    -0.81
     Its
    -0.75
    <eos>
    -0.68
     its
    -0.65
    Its
    -0.63
     
    -0.61
    ↵↵
    -0.60
     (
    -0.59
     [
    -0.58
     d
    -0.53
    POSITIVE LOGITS
     itſelf
    1.39
     myſelf
    1.37
     himſelf
    1.24
     raiſ
    1.21
     Jefus
    1.16
     becauſe
    1.13
     themſelves
    1.12
     doubtnut
    1.08
     ſte
    1.06
     poffe
    1.05
    Activations Density 0.178%

    No Known Activations