INDEX

Explanations

code snippets including "get", "set", "return", and "new Value".

oai_token-act-pair · gemini-2.0-flash

code delimiters

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

чко

-0.46

 perang

-0.45

maro

-0.42

ma

-0.40

یه

-0.39

</blockquote>

-0.38

 common

-0.38

 articles

-0.38

必要がある

-0.38

POSITIVE LOGITS

DockStyle

1.08

abestanden

1.05

 للاسماء

1.02

 للمعارف

1.00

IntoConstraints

0.93

extAlignment

0.93

OGND

0.93

 يتيمه

0.92

 متعلقه

0.87

TagMode

0.85

Activations Density 2.080%

code snippets including "get", "set", "return", and "new Value".

code delimiters

No Comments

No Known Activations