INDEX

Explanations

the word "token" and similar words like "tokens"

oai_token-act-pair · gemini-2.0-flash

token

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 token

-2.50

token

-2.39

Token

-2.20

 Token

-2.09

 tokens

-1.84

TOKEN

-1.81

 TOKEN

-1.68

 Tokens

-1.51

tokens

-1.45

Tokens

-1.44

POSITIVE LOGITS

 متعلقه

0.75

EnableWeb

0.64

 Chwiliwch

0.61

ⓧ

0.60

bewerken

0.58

 policiales

0.56

abestanden

0.55

!*\

0.53

pozorn

0.53

dma

0.53

Activations Density 0.259%

the word "token" and similar words like "tokens"

token

No Known Activations