INDEX

Explanations

code snippets including programming keywords

oai_token-act-pair · gemini-2.0-flash

Code and database context

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

ofition

-0.53

Contours

-0.48

gesteld

-0.48

Interface

-0.45

Options

-0.45

Bundle

-0.45

Platforms

-0.45

Configuration

-0.45

nefs

-0.44

hő

-0.44

POSITIVE LOGITS

Geplaatst

0.69

 "..\..\..\

0.61

 Audiodateien

0.59

 bezeichneter

0.56

MemberId

0.55

 LoginComponent

0.55

 Савезне

0.54

 RIAA

0.54

 Sacrament

0.54

FromNib

0.54

Activations Density 4.111%

code snippets including programming keywords

Code and database context

No Known Activations