INDEX

Explanations

the word 'there' followed by a form of 'to be'

oai_token-act-pair · gemini-2.0-flash

There

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

-0.45

 Paul

-0.44

Pau

-0.44

Paul

-0.43

 име

-0.43

ain

-0.41

nes

-0.41

No

-0.41

cks

-0.40

POSITIVE LOGITS

GraphicsUnit

1.38

 Мексичка

1.13

 >=",

1.05

EDEFAULT

1.04

 esternos

1.02

featureID

1.01

Tikang

1.00

NameInMap

0.98

IsContent

0.95

tvguidetime

0.94

Activations Density 0.281%

the word 'there' followed by a form of 'to be'

There

No Comments

No Known Activations