INDEX

Explanations

short introductions or summaries

oai_token-act-pair · gemini-2.0-flash

text summaries

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 overview

-1.09

 summary

-0.99

 Überblick

-0.92

 glimpse

-0.90

 view

-0.88

 OVERVIEW

-0.87

 brief

-0.86

 preview

-0.82

 glimpses

-0.81

 description

-0.79

POSITIVE LOGITS

queryInterface

0.59

ритори

0.49

."],

0.48

InjectAttribute

0.47

Datuak

0.45

acquisto

0.43

webElementGuid

0.43

спеди

0.43

SDAY

0.42

צלחה

0.41

Activations Density 1.567%

short introductions or summaries

text summaries

No Comments

No Known Activations