INDEX

Explanations

references to prior material

oai_token-act-pair · gemini-2.0-flash

above

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 Theſe

-0.99

 Мексичка

-0.88

 متعلقه

-0.77

 hereof

-0.76

 foregoing

-0.74

<bos>

-0.73

 ſame

-0.72

WireFormatLite

-0.71

 RSSSF

-0.71

 aforesaid

-0.70

POSITIVE LOGITS

 another

0.46

another

0.44

 davvero

0.41

 vraiment

0.41

 outra

0.40

 другого

0.40

['

0.39

घ

0.39

fjspx

0.39

всегда

0.38

Activations Density 2.094%

references to prior material

above

No Comments

No Known Activations