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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6908
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns in the context of recounting experiences and beliefs.

    oai_token-act-pair · gemini-2.0-flash

    Discussing previous actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    consider
    -0.77
     considering
    -0.72
     consideration
    -0.70
     discuss
    -0.70
    considering
    -0.69
     consider
    -0.69
     discussing
    -0.65
    Consider
    -0.65
    ideration
    -0.65
     Consideration
    -0.64
    POSITIVE LOGITS
     transfieras
    0.75
     विश्वसनीयता
    0.65
    сылкі
    0.59
     nakalista
    0.59
    хьтан
    0.58
    PMailer
    0.56
    Gön
    0.55
    PullParser
    0.55
    ReusableCell
    0.54
    SBATCH
    0.54
    Activations Density 7.200%

    No Known Activations