© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7601
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and related verb conjugations

    oai_token-act-pair · gemini-2.0-flash

    personal pronouns and statements

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

    I/we

    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
     protoimpl
    -0.74
     jadx
    -0.56
    #+#
    -0.55
    AutoScaleMode
    -0.52
     APPE
    -0.51
     gynnwys
    -0.51
     Surround
    -0.51
     patro
    -0.48
     Apes
    -0.48
    Norm
    -0.48
    POSITIVE LOGITS
     shall
    0.53
     mergeFrom
    0.53
    URLException
    0.52
    väg
    0.49
    dings
    0.49
    '],
    0.49
    '))
    0.48
     createSlice
    0.48
    shall
    0.47
    StructEnd
    0.47
    Activations Density 0.702%

    No Known Activations