INDEX

Explanations

hexadecimal numbers and related characters, and capitalized words used for names in code and tables

oai_token-act-pair · gemini-2.0-flash

code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

styleType

-0.92

 initComponents

-0.89

RenderAtEndOf

-0.89

MigrationBuilder

-0.88

DockStyle

-0.87

parsedMessage

-0.87

 '\\;'

-0.86

yntaxException

-0.86

 "..\..\

-0.85

InitVars

-0.84

POSITIVE LOGITS

0.54

0.48

0.46

0.45

minlength

0.44

Activations Density 3.133%

hexadecimal numbers and related characters, and capitalized words used for names in code and tables

code

No Comments

No Known Activations