INDEX

Explanations

syntax from programming languages, especially symbols used in JSON-like formats

oai_token-act-pair · gemini-2.0-flash

say code objects

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

脚注の使い方

-0.76

SharedCtor

-0.74

Personensuche

-0.74

 Wikimedijinoj

-0.71

клопе

-0.68

:✨

-0.67

 <<<<<<<<<<<<<<

-0.64

tonode

-0.63

BibitemShut

-0.61

protoimpl

-0.60

POSITIVE LOGITS

thâu

0.67

 object

0.63

 thousands

0.60

object

0.59

 millions

0.56

 objeto

0.54

 IndexPath

0.54

 milliers

0.53

 million

0.52

obj

0.52

Activations Density 1.448%

syntax from programming languages, especially symbols used in JSON-like formats

say code objects

No Comments

No Known Activations