© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13079
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and words associated with familial relationships, often also identifying death/betrayal

    oai_token-act-pair · gemini-2.0-flash

    death and loss

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    tvguidetime
    -0.81
     ProtoMessage
    -0.80
    ंदीखरीदारी
    -0.76
     intptr
    -0.72
     initComponents
    -0.71
    +#+#
    -0.70
    principalTable
    -0.69
    rrggbb
    -0.68
    ItemBackground
    -0.65
     виправивши
    -0.65
    POSITIVE LOGITS
    ass
    0.50
    dem
    0.48
     passing
    0.46
    be
    0.45
    atiques
    0.43
    r
    0.43
    Be
    0.43
    ma
    0.43
     zá
    0.42
    ali
    0.41
    Activations Density 3.009%

    No Known Activations