INDEX

Explanations

angle bracket enclosed code and JSON-like data structures

oai_token-act-pair · gemini-2.0-flash

Code snippets

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

↵

-0.82

↵↵

-0.63

-0.53

—

-0.50

’

-0.49

ma

-0.48

-0.47

-0.46

Ma

-0.45

Ma

-0.44

POSITIVE LOGITS

 itſelf

1.01

 myſelf

0.96

ConstraintMaker

0.95

 surla

0.94

 betweenstory

0.94



0.91

 themſelves

0.91

 raiſ

0.89

adaptiveStyles

0.89

 himſelf

0.88

Activations Density 1.925%

angle bracket enclosed code and JSON-like data structures

Code snippets

No Comments

No Known Activations