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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12328
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal battles, complaints, reports, investigations, and freedom

    oai_token-act-pair · gemini-2.0-flash

    references to self or identity

    np_token-act-pair-logits · gpt-4o-mini

    self

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    intios
    -0.54
    Пло
    -0.44
     yıllar
    -0.44
    remera
    -0.43
    MigrationBuilder
    -0.42
     deme
    -0.42
    conceito
    -0.42
    apatilla
    -0.41
    toPromise
    -0.41
    λώ
    -0.40
    POSITIVE LOGITS
     self
    1.62
     Self
    1.39
    self
    1.31
    Self
    1.28
     SELF
    1.18
    SELF
    1.07
     Selbst
    0.94
    自我
    0.89
    Selbst
    0.85
     voluntarily
    0.79
    Activations Density 2.844%

    No Known Activations