© 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. 16158
    Prev
    Next
    INDEX
    Explanations

    personal opinions and reflections, often using "I" and discussing feelings or experiences.

    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
     Their
    -0.72
    Their
    -0.69
     виправивши
    -0.66
     Leur
    -0.65
    Its
    -0.63
     kanilang
    -0.63
     kaynağından
    -0.62
     Its
    -0.62
    heir
    -0.61
     Leurs
    -0.60
    POSITIVE LOGITS
     my
    2.08
     our
    1.54
    my
    1.51
     mine
    1.46
     mijn
    1.43
    我的
    1.34
     meiner
    1.27
     meinen
    1.24
     моих
    1.22
     моего
    1.21
    Activations Density 6.657%

    No Known Activations