INDEX

Explanations

references to versions or editions of publications or events

oai_token-act-pair · gemini-2.0-flash

edition

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Efq

-1.86

 myſelf

-1.84

 Monfieur

-1.76

 Shakspeare

-1.73

 Cæsar

-1.67

 poffible

-1.63

 itſelf

-1.59

 Houſe

-1.56

 againſt

-1.55

 Shaksp

-1.55

POSITIVE LOGITS

1.05

the

1.04

...

0.95

↵

0.91

0.84

<eos>

0.84

0.81

The

0.80

Activations Density 0.969%

references to versions or editions of publications or events

edition

No Comments

No Known Activations