INDEX

Explanations

scientific writing, often with a conclusion or transition indicated by terms such as 'thus', 'however', 'therefore'.

oai_token-act-pair · gemini-2.0-flash

comma

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

曖昧さ回避

-0.86

Personensuche

-0.77

GOTREF

-0.75

 purpoſe

-0.74

 ſeveral

-0.72

 Савезне

-0.72

 ſind

-0.72

 Anſ

-0.72

 GenerationType

-0.71

 fubject

-0.71

POSITIVE LOGITS

<eos>

0.58

di

0.55

0.51

0.47

0.45

0.43

sud

0.43

OrNil

0.43

nois

0.42

↵↵

0.42

Activations Density 10.891%

scientific writing, often with a conclusion or transition indicated by terms such as 'thus', 'however', 'therefore'.

comma

No Comments

No Known Activations