INDEX

Explanations

words associated with reports, studies, and data

oai_token-act-pair · gemini-2.0-flash

Evidence

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 says

-1.17

 saying

-1.17

 mengatakan

-1.13

says

-1.12

 stating

-1.11

saying

-1.09

said

-1.07

 said

-1.07

 Says

-1.05

 suggests

-1.04

POSITIVE LOGITS

quiao

0.56

RectangleBorder

0.56

UnknownFields

0.54

NOPQRST

0.54

 Normdatei

0.53

complexContent

0.52

RegistryLite

0.52

']);

0.51

))/

0.50

autique

0.48

Activations Density 0.757%

words associated with reports, studies, and data

Evidence

No Comments

No Known Activations