© 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. 1167
    Prev
    Next
    INDEX
    Explanations

    the word "years" and sometimes "days" referring to the passage of time.

    oai_token-act-pair · gemini-2.0-flash

    say "ago"

    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
    OGND
    -0.55
    irm
    -0.47
    fug
    -0.45
    mom
    -0.44
    irt
    -0.44
    OBJ
    -0.44
     olje
    -0.44
     Ol
    -0.43
    Au
    -0.43
     các
    -0.43
    POSITIVE LOGITS
     Efq
    0.79
     raiſ
    0.78
     ſta
    0.76
     deſt
    0.72
     ſhe
    0.72
    ConstraintMaker
    0.69
    #+#
    0.69
     Houſe
    0.68
     poffible
    0.68
     themſelves
    0.67
    Activations Density 3.140%

    No Known Activations