INDEX

Explanations

descriptions of academic research and medical occupations

oai_token-act-pair · gemini-2.0-flash

Code/unusual words

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

 definitive

-0.40

ODE

-0.40

się

-0.39

brü

-0.38

ode

-0.38

gled

-0.37

 сте

-0.37

itect

-0.36

 input

-0.35

GOD

-0.35

POSITIVE LOGITS

StructEnd

1.04

 propOrder

1.03

UnusedPrivate

0.99

 ddelweddau

0.99

 ModelExpression

0.98

 للاسماء

0.94

 ujednoznacz

0.94

 resourceCulture

0.91

ThroughAttribute

0.87

 للمعارف

0.87

Activations Density 1.858%

descriptions of academic research and medical occupations

Code/unusual words

No Comments

No Known Activations