INDEX

Explanations

occurrences of the word "it"

oai_token-act-pair · gemini-2.0-flash

it

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 ujednoznacz

-0.52

 <<<<<<<<<<<<<<

-0.49

 PATENT

-0.47

Vorlage

-0.45

DataMember

-0.45

Архівовано

-0.44

 unmute

-0.44

 Yunus

-0.43

lético

-0.41

Schloss

-0.41

POSITIVE LOGITS

 кӀ

0.67

AndEndTag

0.64

Should

0.63

 متحده

0.62

 shouldn

0.61

should

0.61

NonQuery

0.60

 shouldnt

0.60

expandindo

0.59

 Himo

0.58

Activations Density 1.144%

occurrences of the word "it"

it

No Comments

No Known Activations