INDEX

Explanations

terms related to electrical connections, often in the context of plugging in devices

oai_token-act-pair · gemini-2.0-flash

plug

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 plug

-2.05

 Plug

-1.84

plug

-1.82

Plug

-1.79

 plugin

-1.66

 plugs

-1.63

plugin

-1.58

 plugins

-1.52

 Plugin

-1.52

 PLUG

-1.51

POSITIVE LOGITS

SequentialGroup

1.00

setVerticalGroup

0.74

ndice

0.73

cshtml

0.69

.*")]

0.69

IContainer

0.68

 <>",

0.66

ieuses

0.65

iotensin

0.65

Activations Density 2.866%

terms related to electrical connections, often in the context of plugging in devices

plug

No Comments

No Known Activations