INDEX

Explanations

the preposition "in" and phrases that include the word "touch"

oai_token-act-pair · gemini-2.0-flash

in

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

 myſelf

-0.67

Efq

-0.66

 quæ

-0.65

 themſelves

-0.63

 étoit

-0.61

 ModelExpression

-0.61

 Cæsar

-0.61

 dévelo

-0.61

 himſelf

-0.59

stretchr

-0.59

POSITIVE LOGITS

UserScript

0.51

getResultList

0.47

 ThreadPool

0.45

########.

0.44

 Penh

0.43

ffine

0.42

posedge

0.41

 Reverso

0.40

 mind

0.39

Activations Density 0.529%

the preposition "in" and phrases that include the word "touch"

in

No Comments

No Known Activations