INDEX

Explanations

the word "number" in specific contexts.

oai_token-act-pair · gemini-2.0-flash

say number

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

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

 numbers

-2.92

 Numbers

-2.78

Numbers

-2.59

numbers

-2.58

 NUMBERS

-2.34

Number

-2.13

 Number

-2.09

 números

-2.03

NUMBER

-2.03

 NUMBER

-1.83

POSITIVE LOGITS

CloseOperation

0.82

AutoScaleMode

0.77

 surla

0.65

 متعلقه

0.63

basicConfig

0.61

 Exacts

0.57

 pinulongan

0.57

oa̍t

0.56

elemField

0.55

/**

0.54

Activations Density 2.275%

the word "number" in specific contexts.

say number

No Comments

No Known Activations